INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

didSet

-0.79

MigrationBuilder

-0.70

:✨

-0.64

 resourceCulture

-0.57

 voorbij

-0.57

Santis

-0.53

 mẽ

-0.52

haustible

-0.52

insatz

-0.51

 visuales

-0.50

POSITIVE LOGITS

TagMode

0.56

Havolalar

0.54

 operations

0.53

SourceChecksum

0.52

HideFlags

0.52

 nearly

0.52

Coordonnées

0.50

nearly

0.49

 terbesar

0.49

的所有

0.49

Activations Density 0.114%

No Comments

No Known Activations