INDEX

Explanations

mathematical notations and symbols

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

Mathematical or scientific expressions

np_acts-logits-general · gemini-2.0-flash

technical and mathematical expressions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yoshi

-0.46

Pr

-0.46

io

-0.46

ar

-0.45

Ar

-0.43

ver

-0.43

les

-0.43

Solid

-0.42

hi

-0.42

POSITIVE LOGITS

Autoritní

0.91

 tartalomajánló

0.88

 مشين

0.87

NameInMap

0.86

 disambiguazione

0.85

 ExecuteAsync

0.83

 للمعارف

0.82

 كومونز

0.80

 MaterialApp

0.78

μφωνα

0.78

Activations Density 0.609%

mathematical notations and symbols

Mathematical or scientific expressions

technical and mathematical expressions

No Comments

No Known Activations