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

LabelTagHelper

-0.71

 estekak

-0.63

onedDateTime

-0.62

stateProvider

-0.62

ContentAlignment

-0.58

::_('

-0.58

+#+#

-0.57

grine

-0.55

Chham

-0.55

matchCondition

-0.54

POSITIVE LOGITS

)|^{

0.57

 biografi

0.56

Personendaten

0.56

 <<<<<<<<<<<<<<

0.55

feira

0.53

chitz

0.52

 gala

0.52

ándola

0.52

 polling

0.52

 testa

0.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.