INDEX

Explanations

numerical data and statistical ranges in the text

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

Numbers with a plus/minus range

np_acts-logits-general · gemini-2.0-flash

numbers and symbols

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

 متعلقه

-0.52

PreExecute

-0.51

featureID

-0.50

NoSuchAlgorithm

-0.48

 getchar

-0.47

UpInside

-0.47

 clearColor

-0.46

Buckets

-0.45

 referenties

-0.44

:✨

-0.44

POSITIVE LOGITS

ScopeManager

0.61

ptid

0.57

GEBURTSDATUM

0.57

 Audiodateien

0.57

 समीक्षाएं

0.55

 tenths

0.55

rías

0.55

cshtml

0.54

genstein

0.52

enumi

0.52

Activations Density 1.031%

numerical data and statistical ranges in the text

Numbers with a plus/minus range

numbers and symbols

No Comments

No Known Activations