INDEX

Explanations

structured data definitions and object properties

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

code structure and keywords

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

fjspx

-0.49

CodedInputStream

-0.41

EndInit

-0.40

bodies

-0.38

lah

-0.35

imm

-0.34

aves

-0.34

su

-0.34

AppMethodBeat

-0.33

iast

-0.33

POSITIVE LOGITS

IntoConstraints

0.66

 GenerationType

0.66

 avoient

0.54

Naissance

0.53

Décès

0.48

 iParam

0.47

sidemargin

0.47

XmlAccessorType

0.46

 Privacidade

0.46

ientôt

0.45

Activations Density 0.035%

structured data definitions and object properties

code structure and keywords

No Comments

No Known Activations