INDEX

Explanations

the beginning of new paragraphs or sections in the text

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

Code, debugging, or warnings

np_acts-logits-general · gemini-2.0-flash

debug and warning logs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Parmi

-0.62

 financières

-0.60

InitVars

-0.56

>";

-0.55

 ritratto

-0.54

 originaux

-0.53

 ordinaires

-0.53

انون

-0.52

σιμοποι

-0.52

imageshack

-0.52

POSITIVE LOGITS

DEBUG

0.78

ArrowToggle

0.72

 Initialized

0.69

 للمعارف

0.69

Datuak

0.67

Przypisy

0.66

BASEPATH

0.61

 مرئيه

0.60

 DEBUG

0.60

Autoritní

0.59

Activations Density 0.034%

the beginning of new paragraphs or sections in the text

Code, debugging, or warnings

debug and warning logs

No Comments

No Known Activations