A JAX Research Toolkit for Visualizing, Manipulating, and Understanding Gemma Models with Multi-modal Support based on Penzai.
-
Updated
Jan 13, 2026 - Jupyter Notebook
A JAX Research Toolkit for Visualizing, Manipulating, and Understanding Gemma Models with Multi-modal Support based on Penzai.
Gemma-4-Free Google DeepMind open-weight LLM (Apache 2.0). Sizes: E2B, E4B, 12B, 26B MoE, 31B Dense. Native vision + audio, 256K context. 85% MMLU Pro, 80% LiveCodeBench. Runs locally via Ollama. Beats Llama 4 & Qwen 3.5 on reasoning. Edge, mobile & agentic coding deployment guides.
A research tool for studying how deception emerges in multi-agent LLM systems and detecting it through activation analysis.
Add a description, image, and links to the gemma-scope topic page so that developers can more easily learn about it.
To associate your repository with the gemma-scope topic, visit your repo's landing page and select "manage topics."