INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 ExecuteAsync

-0.65

transQ

-0.56

invokeLater

-0.56

RegressionTest

-0.55

parsedMessage

-0.52

onOptions

-0.51

onViewCreated

-0.49

UserScript

-0.49

Clik

-0.47

AsUp

-0.47

POSITIVE LOGITS

Attribute

1.02

 Attribute

0.78

attribute

0.68

 attribute

0.65

 AttributeSet

0.55

ATTRIBUTE

0.54

Attributes

0.47

ATTRIBUTES

0.46

AttributeValue

0.46

 Attributes

0.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.