INDEX

Explanations

specific geographic locations or addresses

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

Numbers within addresses or references

np_acts-logits-general · gemini-2.0-flash

numbers followed by a word or punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

Chham

-0.85

ScopeManager

-0.82

enumi

-0.81

ValueStyle

-0.81

MigrationBuilder

-0.79

+:+

-0.77

 nargin

-0.76

 szóci

-0.76

RegistryLite

-0.76

GEBURTSDATUM

-0.76

POSITIVE LOGITS

0.69

0.66

0.65

0.64

0.61

0.57

0.56

Activations Density 0.507%

specific geographic locations or addresses

Numbers within addresses or references

numbers followed by a word or punctuation

No Comments

No Known Activations