Gemma Scope 2: Interpretability Tools Released Across Entire Gemma 3 Family
DeepMind has released Gemma Scope 2, an open interpretability toolkit covering the full Gemma 3 model family. The release extends the original Gemma Scope effort to provide the AI safety community with tools for understanding complex language model behavior. By making these tools openly available across all Gemma 3 variants, DeepMind aims to support mechanistic interpretability research at scale.
Related guides (4)
Google DeepMind
Google DeepMind: Frontier AI Across Models, Robotics, and Scientific Discovery
Related events (8)
Google releases Gemma 2 2B, ShieldGemma and Gemma Scope
Google released three new additions to the Gemma ecosystem: Gemma 2 2B, a small open-weights language model; ShieldGemma, a safety-focused classifier model; and Gemma Scope, an interpretability toolset. These releases expand the Gemma family with a smaller, more accessible model alongside dedicated safety and interpretability infrastructure. The announcement was published on the Hugging Face blog, indicating integration with the HF ecosystem.
Welcome Gemma 3: Google's All-New Multimodal, Multilingual, Long-Context Open LLM
Google has released Gemma 3, a new family of open-weights large language models featuring multimodal capabilities, multilingual support, and extended context windows. The Hugging Face blog post introduces the model family and its key features. Gemma 3 represents a significant update to Google's open-weights model line, expanding beyond text-only capabilities to include vision and broader language coverage.
Gemma 3n Fully Available in the Open-Source Ecosystem
Google's Gemma 3n model has been integrated into the open-source ecosystem via Hugging Face, making it broadly accessible for developers and researchers. The announcement covers availability of the model weights and tooling support within the Hugging Face platform. Gemma 3n is designed for efficient on-device inference, targeting mobile and edge deployment scenarios. This release extends the open-weights frontier model landscape with a multimodal-capable, efficiency-focused architecture.
Introducing Gemma 3n: The Developer Guide
Google DeepMind has published a developer-focused guide introducing Gemma 3n, a new model in the Gemma open-weights family. The announcement is directed at the developer community and appears to describe architecture, usage, and integration details for the new release. As a Tier 1 source announcement, this represents a notable addition to Google's open-weights model lineup.
Welcome Gemma 2 - Google's new open LLM
Google released Gemma 2, a new open-weights large language model, announced via the Hugging Face blog. The post covers integration with the Hugging Face ecosystem and highlights the model's capabilities. Gemma 2 represents Google's continued investment in open-weight model releases to compete in the open-source LLM space.
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
Google DeepMind has released Gemma 3 270M, a 270-million parameter compact language model added to the Gemma 3 family. The model is positioned as a highly specialized, hyper-efficient tool for resource-constrained deployments. This extends the Gemma 3 lineup into the sub-billion parameter range, targeting edge and on-device use cases.
Introducing Gemma 3
Google DeepMind has released Gemma 3, described as the most capable model runnable on a single GPU or TPU. The announcement comes from DeepMind's official blog, indicating a new generation of the open-weights Gemma model family. Specific capability details, parameter counts, and benchmark results are not included in the provided body text.
Interpretability study of DiffusionGemma reveals novel diffusion-specific reasoning phenomena
Researchers investigate the reasoning transparency of DiffusionGemma, a diffusion-based language model, decomposing transparency into variable and algorithmic components. They show that mapping information through an interpretable token bottleneck reduces DiffusionGemma's opaque serial depth from 28.6X to just 1.1X that of autoregressive Gemma 4, with no performance loss. Interpretability case studies uncover diffusion-specific phenomena including non-chronological reasoning, token smearing, and intermediate-context reasoning. Monitorability tests find DiffusionGemma comparable to Gemma 4, suggesting diffusion LMs are not inherently less amenable to safety oversight.