INDEX

Explanations

programming language syntax and structure

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

code and technical terms

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

 للاسماء

-0.66

WithMany

-0.65

NamedQueries

-0.56

 propOrder

-0.56

providedIn

-0.56

RuleContext

-0.55

WaitGroup

-0.54

ExecuteReader

-0.52

HtmlAttribute

-0.51

EClass

-0.50

POSITIVE LOGITS

styleUrls

0.42

httphttps

0.37

fashion

0.37

 makeStyles

0.35

 BeautifulSoup

0.34

 fashion

0.33

postcss

0.32

orithmic

0.31

 uygula

0.30

系

0.30

Activations Density 0.000%

programming language syntax and structure

code and technical terms

No Comments

No Known Activations