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

-0.38

CreateModel

-0.33

élimin

-0.32

<eos>

-0.32

-0.31

createNew

-0.31

wo

-0.30

do

-0.30

create

-0.29

 trial

-0.29

POSITIVE LOGITS

tagHelper

0.96

fjspx

0.84

Attribute

0.81

ValueStyle

0.79

WEBPACK

0.79

 CreateTagHelper

0.78

BibitemShut

0.75

DoubleQuotes

0.73

InjectAttribute

0.72

 Attribute

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.