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

Хьажоргаш

-0.56

 consult

-0.50

 nationalen

-0.47

éen

-0.47

Nguồn

-0.46

 points

-0.46

oida

-0.46

 условиях

-0.45

 Pond

-0.44

UnitTesting

-0.43

POSITIVE LOGITS

IsMutable

0.84

脚注の使い方

0.75

 متعلقه

0.75

Autoritní

0.70

GIVEREF

0.69

HasAnnotation

0.66

 propOrder

0.63

 الرياضيه

0.63

 doInBackground

0.62

 GenerationType

0.61

Activations Density 0.059%

No Comments

No Known Activations