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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Krakowie

-0.41

tvguidetime

-0.39

atouille

-0.38

 legais

-0.36

ętr

-0.35

 esportes

-0.35

 akku

-0.35

NamedQueries

-0.35

 darbu

-0.35

are

-0.34

POSITIVE LOGITS

UseVisualStyle

6.13

GraphicsUnit

0.78

 propOrder

0.77

PreferredItem

0.76

AutoScaleMode

0.74

 AssemblyTitle

0.73

TabStop

0.71

DebuggerNonUser

0.68

AutoScale

0.66

RefNanny

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.