INDEX

Explanations

conjunctions and relational phrases

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

specialized/code contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

@"/

-0.56

nonatomic

-0.55

êter

-0.47

XmlIgnore

-0.47

 незавершена

-0.46

NullCheck

-0.46

__(/*!

-0.45

 cotone

-0.45

ObjectModel

-0.44

BooleanField

-0.44

POSITIVE LOGITS

 nakalista

0.81

 الحره

0.71

 通販

0.68

inderella

0.68

حياتها

0.66

 leaſt

0.63

bibfield

0.62

 تانيه

0.60

 LoginComponent

0.57

Osi

0.57

Activations Density 0.318%

conjunctions and relational phrases

specialized/code contexts

No Comments

No Known Activations