INDEX

Explanations

programming or data structure-related terminology

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

Java method parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.71

RenderAtEndOf

-0.66

 kasarigan

-0.65

!*\

-0.62

transQ

-0.53

 незавершена

-0.53

EnableWeb

-0.50

AutoScaleMode

-0.48

UseVisualStyle

-0.48

LookAnd

-0.48

POSITIVE LOGITS

 Partager

0.38

 hohem

0.37

Soorten

0.37

 Geruch

0.37

 arru

0.36

 jezik

0.36

 Económica

0.36

 Männern

0.35

 Decke

0.35

 Worten

0.35

Activations Density 0.007%

programming or data structure-related terminology

Java method parameters

No Comments

No Known Activations