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

Hentet

-1.02

ScopeManager

-0.98

 الرياضيه

-0.89

-0.84

ьажоргаш

-0.82

featureID

-0.79

MLLoader

-0.79

 فريبيس

-0.76

ⓘ

-0.73

 Normdatei

-0.73

POSITIVE LOGITS

ern

0.51

no

0.47

pro

0.46

ItemClick

0.45

for

0.44

at

0.44

いわ

0.43

Pro

0.43

ERN

0.43

py

0.42

Activations Density 0.327%

No Comments

No Known Activations