INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 szóci

-0.93

 defaultstate

-0.81

findpost

-0.80

 HomeComponent

-0.79

ContentAsync

-0.75

styleType

-0.75

 חיצוניים

-0.73

PreferredItem

-0.72

 виправивши

-0.72

httphttps

-0.71

POSITIVE LOGITS

月

0.95

월

0.73

0.57

 September

0.56

 lune

0.56

月

0.56

 libere

0.56

tears

0.56

 Moon

0.55

 Lune

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.