INDEX

Explanations

technical specifications and parameters related to software frameworks

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

target framework versions

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

rungsseite

-0.50

RenderAtEndOf

-0.46

 propOrder

-0.45

ữu

-0.45

astify

-0.43

UpInside

-0.41

ChildScrollView

-0.39

FXML

-0.38

UrlResolution

-0.37

MLLoader

-0.37

POSITIVE LOGITS

Personensuche

0.54

 Stö

0.47

SdkVersion

0.47

 kasarigan

0.47

JNIEnv

0.45

modern

0.44

 compatibility

0.44

 phù

0.44

الحياه

0.43

 attainable

0.43

Activations Density 0.030%

technical specifications and parameters related to software frameworks

target framework versions

No Comments

No Known Activations