INDEX

Explanations

technical terms related to imaging and analysis in scientific research

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

specific objects

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

ECONDS

-0.46

 needlessly

-0.41

 unnecessarily

-0.39

%"),

-0.39

 mẽ

-0.38

 CURIAM

-0.38

 counted

-0.38

esgue

-0.37

 Perpetual

-0.37

☉

-0.36

POSITIVE LOGITS

 subtle

0.61

細節

0.57

 subtleties

0.56

 Veränderungen

0.55

 detaljer

0.54

 objects

0.54

 elusive

0.53

subtle

0.52

 details

0.52

curities

0.52

Activations Density 0.311%

technical terms related to imaging and analysis in scientific research

specific objects

No Comments

No Known Activations