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

strcmp

-0.44

 aimer

-0.44

 nhiêu

-0.43

-0.42

Hentet

-0.42

 Bradshaw

-0.41

-0.40

side

-0.39

med

-0.39

jącym

-0.39

POSITIVE LOGITS

RenderAtEndOf

0.91

Personendaten

0.86

 calendriers

0.82

BeginContext

0.79

 censiti

0.77

 HasFactory

0.73

AutoresizingMask

0.73

="@+

0.71

 wireType

0.69

verwijspagina

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.