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

 Мексичка

-1.20

ScopeManager

-0.85

ChildScrollView

-0.81

 ComVisible

-0.81

 насељу

-0.78

 ModelExpression

-0.77

تقاوى

-0.74

AxisAlignment

-0.73

Portail

-0.71

ngdoc

-0.71

POSITIVE LOGITS

0.86

 <<<<<<<<<<<<<<

0.58

 saken

0.53

Lähteet

0.52

 demikian

0.51

。

0.49

 aldus

0.47

บัติ

0.47

这里是

0.46

।

0.46

Activations Density 0.028%

No Comments

No Known Activations