INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

kva

-0.54

 reven

-0.54

 determination

-0.52

PTION

-0.50

 συν

-0.50

ByDefault

-0.49

erville

-0.49

ondo

-0.48

igu

-0.48

encre

-0.47

POSITIVE LOGITS

UpInside

0.87

IntoConstraints

0.82

ReusableCell

0.81

MethodManager

0.77

tvguidetime

0.77

DrawerToggle

0.75

0.72

bufio

0.70

Clik

0.69

izontal

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.