INDEX

Explanations

programming-related terms and code structure components

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

sbin and erb

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

instancetype

-0.39

existsSync

-0.38

ActivityCompat

-0.36

της

-0.36

disposing

-0.36

 nature

-0.35

RectangleBorder

-0.35

MENAFN

-0.34

nature

-0.34

Naissance

-0.34

POSITIVE LOGITS

eqnarray

2.53

toHaveBeenCalled

0.72

webElementXpaths

0.70

 tartalomajánló

0.67

beqa

0.64

inheritDoc

0.61

 kohdetta

0.59

 PyLong

0.58

vorschau

0.57

multline

0.57

Activations Density 0.002%

programming-related terms and code structure components

sbin and erb

No Comments

No Known Activations