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

loyees

-0.60

inaison

-0.56

便

-0.52

PYX

-0.51

 <=",

-0.51

HasForeignKey

-0.50

thenReturn

-0.50

 namelijk

-0.49

Identyfik

-0.49

 Majefty

-0.48

POSITIVE LOGITS

iprot

0.63

 الرياضيه

0.59

featureID

0.57

 sumpay

0.57

psies

0.56

 εδώ

0.55

map

0.54

География

0.54

ArgsConstructor

0.54

cling

0.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.