INDEX

Explanations

documentation comment syntax used in code

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

PHP class names

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

 BigNumberish

-0.45

ussure

-0.43

libft

-0.40

PlayerPrefs

-0.40

 useState

-0.40

 Obrador

-0.40

 boolean

-0.38

 éter

-0.38

LLocation

-0.38

 Wien

-0.37

POSITIVE LOGITS

RectangleBorder

0.44

adpleegd

0.44

 ब्रेकडाउन

0.43

 najdete

0.42

 للمعارف

0.42

 BoxDecoration

0.42

UnitTesting

0.42

bootstrapcdn

0.42

 fisik

0.40

Vorlage

0.40

Activations Density 0.001%

documentation comment syntax used in code

PHP class names

No Comments

No Known Activations