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

MLLoader

-0.62

stylers

-0.57

fromnode

-0.53

SequentialGroup

-0.53

Personendaten

-0.52

évaluateur

-0.48

UnusedPrivate

-0.48

 محفوظة

-0.48

 चीज़ों

-0.47

blockList

-0.45

POSITIVE LOGITS

 EconPapers

0.50

 supérieurs

0.45

 supérieures

0.42

hôte

0.42

 Covid

0.41

 zarar

0.40

 Gelegenheit

0.40

 indé

0.39

 artistique

0.38

SaveChangesAsync

0.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.