INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Samaria

-0.61

購入

-0.59

 cytok

-0.59

 Cæsar

-0.56

 angekommen

-0.54

 Valky

-0.54

 Bernoulli

-0.53

 Aphrodite

-0.53

 lyre

-0.53

 uchiha

-0.52

POSITIVE LOGITS

the

1.28

1.06

FOR

1.03

For

1.02

FOR

0.94

its

0.86

an

0.86

 their

0.85

 those

0.85

ForValue

0.83

Activations Density 0.000%

No Known Activations

This feature has no known activations.