Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Summary
Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
Opens in a new tab. Subvolts summarizes and links; the full piece belongs to Google DeepMind Blog.
Where the other five stand
Related: OpenAI: Update to GPT-5 System Card: GPT-5.2 · Meta: Introducing SAM Audio: The First Unified Multimodal Model for Audio Separation | AI at Meta
Hype check
2/5Worth a look
Rated low: routine. Worth knowing, not worth rearranging your day for.
Prior coverage our earlier items on the same thing
- Improved Gemini audio models for powerful voice experiencesGoogle DeepMind Blog
- Deepening our partnership with the UK AI Security InstituteGoogle DeepMind Blog
- FACTS Benchmark Suite: Systematically evaluating the factuality of large language modelsGoogle DeepMind Blog
- Mapping, modeling, and understanding nature with AIGoogle DeepMind Blog
- T5Gemma: A new collection of encoder-decoder Gemma modelsGoogle DeepMind Blog
- MedGemma: Our most capable open models for health AI developmentGoogle DeepMind Blog
Questions people ask
- Where can I read the full story?
- On Google DeepMind Blog. The "Read this on Google DeepMind Blog" link above opens the original in a new tab. Subvolts publishes a summary and analysis, never the full piece.
- What does this mean for Gemini?
- Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma…
More from Google DeepMind Blog 99 more
Page generated Sep 3, 2026. Summaries are Subvolts' own; the story belongs to Google DeepMind Blog.