INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.81

PropertyChanging

-0.59

EndInit

-0.57

PerformLayout

-0.57

 esternos

-0.56

styleType

-0.56

JsonFormat

-0.55

رشف

-0.54

üyada

-0.54

UnusedPrivate

-0.54

POSITIVE LOGITS

 ouverte

1.20

 ouvert

0.65

 ouvertes

0.65

 abierta

0.56

 aberta

0.56

 ouverts

0.51

 abierto

0.49

 abiertas

0.48

بوابة

0.48

 deschis

0.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.