INDEX

Explanations

technical terms related to Android application components and intents

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

package and component 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

 capelli

-0.34

+:+

-0.34

ApiModelProperty

-0.34

 makeStyles

-0.32

:+:

-0.32

useState

-0.32

enterOuterAlt

-0.32

EndProject

-0.31

sizer

-0.31

 թվական

-0.31

POSITIVE LOGITS

ComponentName

1.26

MIDDLEWARE

0.50

VIAF

0.50

TestingModule

0.49

 EconPapers

0.48

 hochzeit

0.48

@[+][

0.48

DIPSETTING

0.47

WebServlet

0.47

 Commando

0.45

Activations Density 0.004%

technical terms related to Android application components and intents

package and component names

No Comments

No Known Activations