INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

VIAF

-0.48

umpang

-0.48

ariki

-0.44

և

-0.44

clen

-0.44

 Flat

-0.43

up

-0.43

heng

-0.43

 Blank

-0.43

 HttpNotFound

-0.42

POSITIVE LOGITS

 MainAxisSize

0.73

contentLoaded

0.71

ScopeManager

0.69

 Signalez

0.66

ValueStyle

0.66

PasswordEncoder

0.65

getDoctrine

0.63

RenderAtEndOf

0.62

TagMode

0.61

ThroughAttribute

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.