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

WithIOException

-0.77

}{*}{

-0.71

EndInit

-0.66

 ressemble

-0.65

__":

-0.64

 <=",

-0.64

 ostavi

-0.63

}{@

-0.63

GOTREF

-0.63

__':

-0.63

POSITIVE LOGITS

 millions

0.75

 billions

0.70

 worldwide

0.64

 growing

0.63

 annually

0.61

growing

0.60

 global

0.60

 Millions

0.59

 jährlich

0.58

Millions

0.57

Activations Density 0.127%

No Comments

No Known Activations