INDEX

Explanations

mentions of Switzerland and its related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Switzerland and Swiss associated terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

richTextPanel

-0.47

 trabal

-0.44

 misure

-0.43

kehr

-0.41

pel

-0.40

force

-0.40

ke

-0.39

乓

-0.39

ca

-0.38

do

-0.38

POSITIVE LOGITS

 Switzerland

0.71

zerland

0.69

Switzerland

0.69

 Suiza

0.66

Swiss

0.59

Schweizer

0.57

 Swiss

0.56

 betweenstory

0.56

 Schweiz

0.55

 Suisse

0.55

Activations Density 0.006%

mentions of Switzerland and its related terms

Switzerland and Swiss associated terms

No Comments

No Known Activations