INDEX

Explanations

numerical values or references in technical or structured data contexts

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

Code or markup with coordinates/parameters

np_acts-logits-general · gemini-2.0-flash

coordinates with brackets

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

ագրություններ

-0.74

 Réponses

-0.59

PROLOG

-0.59

 PhpStorm

-0.58

 estekak

-0.58

FormTagHelper

-0.56

 بيها

-0.55

المشاركات

-0.55

DIPSETTING

-0.54

 warming

-0.53

POSITIVE LOGITS

findpost

0.89

 وتسجيلات

0.58

InSection

0.50

astéroïdes

0.48

culadora

0.45

GrantedAuthority

0.45

Than

0.45

 thôi

0.44

зайн

0.43

üglich

0.43

Activations Density 0.174%

numerical values or references in technical or structured data contexts

Code or markup with coordinates/parameters

coordinates with brackets

No Comments

No Known Activations