INDEX

Explanations

references to spreadsheets and data exporting details

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

data tables and formats

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

in

-0.31

la

-0.30

dic

-0.30

-0.29

ita

-0.29

ata

-0.28

oko

-0.28

quad

-0.28

span

-0.28

POSITIVE LOGITS

TypedDataSet

0.79

 DataTable

0.75

PropertyChanging

0.74

 tables

0.70

writerow

0.68

uxxxx

0.68

 MainAxisSize

0.66

 समीक्षाओं

0.65

tagHelperRunner

0.65

şört

0.65

Activations Density 0.112%

references to spreadsheets and data exporting details

data tables and formats

No Comments

No Known Activations