INDEX

Explanations

gene names and related biological terms

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

after capitalized words/names

np_acts-logits-general · gemini-2.0-flash

company names and acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.62

»

-0.54

and

-0.53

“

-0.52

-0.51

-0.50

«

-0.50

in

-0.49

-0.48

to

-0.48

POSITIVE LOGITS

 فريبيس

1.12

bootstrapcdn

0.94

CloseOperation

0.86

تقاوى

0.85

 Anſ

0.85

 оригіналу

0.84

Personendaten

0.84

expandindo

0.83

 Wikimedijinoj

0.82

 houſe

0.82

Activations Density 0.970%

gene names and related biological terms

after capitalized words/names

company names and acronyms

No Comments

No Known Activations