INDEX

Explanations

identifiers related to coding structures and data organization

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

`blockList`, `IMPORTED`

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

Personendaten

-0.61

GEBURTSDATUM

-0.57

Suara

-0.54



-0.50

 appContext

-0.48

 مشين

-0.47

NameInMap

-0.47

formKey

-0.46

usermodel

-0.44

__(/*!

-0.44

POSITIVE LOGITS

SuppressLint

1.18

makeConstraints

0.99

InjectMocks

0.94

+#+#

0.66

ChildScrollView

0.59

mybatisplus

0.59

RequiresApi

0.57

jspx

0.56

IntoConstraints

0.54

BeforeEach

0.51

Activations Density 0.001%

identifiers related to coding structures and data organization

`blockList`, `IMPORTED`

No Comments

No Known Activations