gemma-2-9b

The 'gemma-2-9b' is a benchmark used to evaluate the performance of large language models, specifically in the context of multilingual capabilities and cross-lingual transfer, particularly for the Bavarian language.

Papers using gemma-2-9b (3)

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection2026Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian2025Interpretable Steering of Large Language Models with Feature Guided Activation Additions2025