INDEX

Explanations

access modifiers in programming languages

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

protected access modifier

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

rungsseite

-0.67

 disambiguazione

-0.64

 aapt

-0.60

PyExc

-0.59

AndEndTag

-0.59

 Paglinawan

-0.59

Portail

-0.56

QMetaType

-0.55

IntoConstraints

-0.53

ParallelGroup

-0.53

POSITIVE LOGITS

protected

0.67

 protected

0.47

 protegido

0.47

 geschützt

0.43

Protected

0.42

abstractmethod

0.41

 protegida

0.39

 skydd

0.37

staticmethod

0.35

ContainerState

0.34

Activations Density 0.003%

access modifiers in programming languages

protected access modifier

No Comments

No Known Activations