INDEX

Explanations

programming and coding elements, particularly related to Android development

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

Code-related content/programming

np_acts-logits-general · gemini-2.0-flash

JetBrains Kotlin imports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 acquis

-0.41

 model

-0.36

 vers

-0.34

acu

-0.34

 mechan

-0.34

 vite

-0.34

-$

-0.33

 auto

-0.33

 inti

-0.32

Geb

-0.31

POSITIVE LOGITS

ValueStyle

1.00

 StatelessWidget

0.90

 nahilalakip

0.83

MessageOf

0.82

AnchorStyles

0.79

AndEndTag

0.77

fjspx

0.77

Datuak

0.76

webElementXpaths

0.75

SourceChecksum

0.73

Activations Density 0.010%

programming and coding elements, particularly related to Android development

Code-related content/programming

JetBrains Kotlin imports

No Comments

No Known Activations