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

 ModelExpression

-0.58

principalColumn

-0.54

 Flü

-0.54

TagMode

-0.52

keyColumn

-0.52

urezza

-0.50

 unknownFields

-0.50

 lại

-0.50

 rapi

-0.50

 moulin

-0.49

POSITIVE LOGITS

مصادر

0.92

TargetApi

0.80

setLayoutManager

0.80

 оригіналу

0.79

 الحره

0.78

OrNil

0.78

KommentareTeilen

0.75

reactstrap

0.74

 viewDidLoad

0.72

HttpFoundation

0.70

Activations Density 0.018%

No Comments

No Known Activations