INDEX

Explanations

scientific terminology and technical notation

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

Mathematical or chemical formulas

np_acts-logits-general · gemini-2.0-flash

medical Abbreviations and text

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

ográficas

-0.35

BeginContext

-0.32

MemoryWarning

-0.32

 незавершена

-0.30

ritus

-0.29

 OMIT

-0.29

|(

-0.29

GIVEREF

-0.29

hiers

-0.29

featureID

-0.28

POSITIVE LOGITS

 pleaſure

0.55

الحياه

0.52

 ſta

0.49

 betweenstory

0.49

 فريبيس

0.49

 lagerfeld

0.49

 filtre

0.48

 perſon

0.48

 oeil

0.48

ArgsConstructor

0.48

Activations Density 2.412%

scientific terminology and technical notation

Mathematical or chemical formulas

medical Abbreviations and text

No Comments

No Known Activations