INDEX

Explanations

technical terms and data representations in scientific discussions

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

Agreement or matching between items, numbers, or ideas

np_acts-logits-general · gemini-2.0-flash

match and agreement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

خاذ

-0.51

권

-0.48

ScopeManager

-0.48

Componentes

-0.47

ólica

-0.45

aperto

-0.45

 contextLoads

-0.45

eca

-0.42

Classification

-0.41

 modifiers

-0.40

POSITIVE LOGITS

 match

2.42

 matching

2.23

 matches

2.12

 matched

2.10

match

2.09

 MATCH

1.96

 Match

1.94

 Matching

1.89

matching

1.86

Match

1.86

Activations Density 0.923%

technical terms and data representations in scientific discussions

Agreement or matching between items, numbers, or ideas

match and agreement

No Comments

No Known Activations