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

InputBorder

-0.51

principalTable

-0.50

PreferredItem

-0.48

TagHelper

-0.45

 '\\;'

-0.42

+#+

-0.41

richTextPanel

-0.38

AndEndTag

-0.38

ungkinan

-0.37

 disambiguazione

-0.37

POSITIVE LOGITS

umented

0.60

 Wikimedijinoj

0.47

المناصب

0.46

parsedMessage

0.44

Kary

0.43

posa

0.43

ECR

0.42

angler

0.41

strconv

0.41

 Lightboxes

0.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.