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

-0.46

 Tsch

-0.46

-0.43

bar

-0.42

en

-0.41

 managed

-0.40

Go

-0.39

bar

-0.39

 Pohl

-0.39

POSITIVE LOGITS

Sqft

5.16

 sqft

1.20

 kasarigan

1.10

WebElementEntity

0.98

Autoritní

0.97

 Савезне

0.95

:✨

0.93

hyrchwyd

0.92

Vidite

0.91

 EconPapers

0.91

Activations Density 0.000%

No Known Activations

This feature has no known activations.