INDEX

Explanations

occurrences of programming-related terms and classes

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

nextInt after Scanner

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

-0.44

HomeAsUp

-0.41

 LoginForm

-0.35

portál

-0.35

TRAILING

-0.35

qJ

-0.35

aix

-0.35

rungsseite

-0.35

she

-0.35

 autorità

-0.35

POSITIVE LOGITS

 Scanner

1.55

 scanner

1.09

Scanner

1.05

scanner

0.89

 scanners

0.86

 Scanning

0.83

 scanning

0.81

canner

0.80

 scan

0.76

 scanned

0.74

Activations Density 0.000%

occurrences of programming-related terms and classes

nextInt after Scanner

No Comments

No Known Activations