INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

wald

-0.55

mis

-0.50

 Layout

-0.48

seln

-0.48

 Mode

-0.48

zag

-0.47

 fury

-0.47

Mode

-0.47

 stopped

-0.46

 stop

-0.46

POSITIVE LOGITS

 crescita

1.01

ISupport

0.98

 growths

0.92

 evolve

0.89

 improvement

0.89

 grows

0.89

 snippetHide

0.88

Bioaccumulative

0.87

 growth

0.87

 migliorare

0.86

Activations Density 0.046%

No Comments

No Known Activations