INDEX

Explanations

elements related to configuration or structural definitions in programming

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

programming language constructs

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

findpost

-0.54

XtraGrid

-0.50

IBarButtonItem

-0.49

(!__

-0.49

RenderAtEndOf

-0.49

ésult

-0.49

adpleegd

-0.48

 betweenstory

-0.48

titleMargin

-0.47

bootstrapcdn

-0.47

POSITIVE LOGITS

rungsseite

0.46

LookAnd

0.44

yntaxException

0.43

awaiter

0.42

ArgsConstructor

0.40

LabelTagHelper

0.37

dotenv

0.36

interopRequire

0.35

PerformLayout

0.34

getenv

0.33

Activations Density 0.000%

elements related to configuration or structural definitions in programming

programming language constructs

No Comments

No Known Activations