Gemma (Google)

2 glitch tokens

These tokens have been publicly documented on this model or model family. Inclusion does not mean that every version still shows the same behavior.

हिंदीखरीदारी

The Devanagari word for “Hindi shopping”, the single most under-trained token in Gemma-7B's vocabulary.

Gemma (Google)Under-trained

A Persian fragment beginning with a zero-width non-joiner (U+200C ZWNJ, an invisible character); the #2 most under-trained token in Gemma-7B.

Gemma (Google)Under-trained