INDEX

Explanations

descriptions of visual attention or focus

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

Body parts involved in perception or action

np_acts-logits-general · gemini-2.0-flash

body part descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 debout

-0.66

clusal

-0.61

AFX

-0.61

shadowRadius

-0.56

 defaultstate

-0.55

VersionUID

-0.55

easeOut

-0.54

 eyeball

-0.54

("$.

-0.53

 otur

-0.52

POSITIVE LOGITS

 AssemblyCulture

0.66

AddTagHelper

0.61

orari

0.55

protoimpl

0.54

 FetchType

0.53

 otomatig

0.52

 protoimpl

0.52

✭✭

0.51

 mergeFrom

0.50

mechanics

0.47

Activations Density 0.162%

descriptions of visual attention or focus

Body parts involved in perception or action

body part descriptions

No Comments

No Known Activations