INDEX

Explanations

instances of structured data or programming constructs

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

foreign languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.44

-0.43

-0.41

-0.39

-0.38

HomeAsUpEnabled

-0.37

POSITIVE LOGITS

ロウィン

0.85

 queſta

0.79

ſehen

0.79

ésultats

0.78

ſcher

0.77

iſen

0.76

iſchen

0.76

 geſch

0.75

 ſind

0.74

 ſehr

0.74

Activations Density 0.015%

instances of structured data or programming constructs

foreign languages

No Comments

No Known Activations