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

 Segal

-0.51

TemporalType

-0.46

 Morin

-0.44

PerformLayout

-0.42

Portale

-0.42

 forgotten

-0.41

 Duggan

-0.41

Життєпис

-0.41

Olvid

-0.40

ona

-0.40

POSITIVE LOGITS

factory

1.08

 FACTORY

0.90

 factory

0.90

 Factory

0.86

FACTORY

0.84

 factories

0.82

Factory

0.79

 Factories

0.77

BeanFactory

0.69

factories

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.