INDEX

Explanations

terms related to scientific or academic credentials, including names and measures

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

Greek letters and accented characters

np_acts-logits-general · gemini-2.0-flash

scientific and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 المعيارى

-1.00

 mergeFrom

-0.80

bootstrapcdn

-0.67

mogat

-0.65

iecie

-0.65

 Carden

-0.64

 femeninos

-0.63

AutoScaleMode

-0.63

andExpect

-0.62

 geslacht

-0.62

POSITIVE LOGITS

 Beyoncé

0.76

 Pokémon

0.75

Pokémon

0.73

 Kraków

0.71

 Montréal

0.71

 Bogotá

0.71

acán

0.69

 Zürich

0.68

 Erdoğan

0.66

 Citroën

0.66

Activations Density 0.466%

terms related to scientific or academic credentials, including names and measures

Greek letters and accented characters

scientific and proper nouns

No Comments

No Known Activations