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

الإنجليزية

-0.77

(!__

-0.74

ScopeManager

-0.73

 EnglishChoose

-0.73

ɵɵ

-0.72

 CreateTagHelper

-0.70

تقاوى

-0.68

 '\\;'

-0.66

 IBOutlet

-0.65

AndEndTag

-0.65

POSITIVE LOGITS

 indisponible

0.58

+][

0.56

 Quelles

0.54

 Ellison

0.53

llos

0.52

imakasih

0.51

ां

0.50

 Nachbarn

0.50

thumbsup

0.49

ള

0.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.