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

 propOrder

-0.62

GEBURTSDATUM

-0.57

󠁢

-0.51

bootstrapcdn

-0.45

XtraReports

-0.44

multer

-0.41

 שוליים

-0.41

Sov

-0.40

Sov

-0.40

 createSlice

-0.39

POSITIVE LOGITS

webElementXpaths

2.27

DbContext

1.57

 виправивши

0.57

dbContext

0.53

存于互联网档案馆

0.51

最快更新

0.51

SuspendLayout

0.51

setVerticalGroup

0.50

adaptiveStyles

0.45

Notae

0.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.