INDEX

Explanations

code-related keywords and concepts

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

handset receiver off the hook

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gnore

-0.36

 underground

-0.32

 stickers

-0.31

麽

-0.31

sqlite

-0.31

nungszeiten

-0.31

 colleg

-0.30

 Signore

-0.30

 allergies

-0.29

회

-0.29

POSITIVE LOGITS

NavController

1.26

 BaseActivity

0.89

脚注の使い方

0.73

ConstraintMaker

0.69

LITERAL

0.69

BeginInit

0.68

escaping

0.67

 wikipagina

0.66

 NavController

0.65

 XCTest

0.64

Activations Density 0.001%

code-related keywords and concepts

handset receiver off the hook

No Comments

No Known Activations