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

MLLoader

-0.41

 señ

-0.39

 wielu

-0.34

fehl

-0.33

 mão

-0.32

 Viele

-0.32

 darauf

-0.31

 huesos

-0.29

 muchas

-0.29

 many

-0.28

POSITIVE LOGITS

 trattano

4.94

GEBURTS

1.02

 tartalomajánló

0.95

 treat

0.95

 treating

0.91

 Treat

0.91

treat

0.90

 treats

0.89

 MainAxisSize

0.87

Treating

0.86

Activations Density 0.000%

No Known Activations

This feature has no known activations.