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

 TType

-0.57

RunWith

-0.57

idity

-0.57

Vorlage

-0.57

mybatisplus

-0.56

soort

-0.55

StoryboardSegue

-0.54

apimachinery

-0.54

verter

-0.53

lihood

-0.53

POSITIVE LOGITS

 disponibilités

0.69

UnusedPrivate

0.65

aarrggbb

0.63

 propOrder

0.60

:][

0.56

XtraReports

0.55

 kaarangay

0.54

Personendaten

0.54

 initComponents

0.53

TypedDataSet

0.52

Activations Density 0.042%

No Comments

No Known Activations