INDEX

Explanations

locations and geographic references

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

after URLs or code snippets

np_acts-logits-general · gemini-2.0-flash

areas and regions

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

 ISNI

-0.65

TAWA

-0.59

 AssemblyCulture

-0.59

skosten

-0.53

 JERSEY

-0.53

県道

-0.53

 AssemblyProduct

-0.52

ുടെ

-0.51

ILabel

-0.50

 utom

-0.50

POSITIVE LOGITS

 area

0.93

 region

0.83

 Area

0.76

 district

0.74

 areas

0.69

region

0.68

area

0.68

地区

0.66

 districts

0.64

ScopeManager

0.61

Activations Density 0.413%

locations and geographic references

after URLs or code snippets

areas and regions

No Comments

No Known Activations