INDEX

Explanations

lines of code, particularly preprocessor directives and comments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

C preprocessor directives

np_acts-logits-general · gemini-2.0-flash

ifndef, pragma, region

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

)_/¯

-0.73

expandindo

-0.61

="#"><

-0.60

ztály

-0.59

ništvo

-0.58

 HasFactory

-0.58

 Italijani

-0.58

textAppearance

-0.56

Obrázky

-0.56

WebVitals

-0.55

POSITIVE LOGITS

region

0.85

 region

0.66

pragma

0.65

endregion

0.64

MessageTagHelper

0.60

Region

0.59

 Region

0.52

kring

0.49

regions

0.49

 REGION

0.48

Activations Density 0.193%

lines of code, particularly preprocessor directives and comments

C preprocessor directives

ifndef, pragma, region

No Comments

No Known Activations