INDEX

Explanations

structured data types and their associated properties

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

foreign words in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

WithMany

-0.69

GEBURTS

-0.68

NameInMap

-0.66

Personendaten

-0.63

GEBURTSDATUM

-0.59

ConstraintMaker

-0.58

onAttach

-0.57

Diwedd

-0.56

IsContent

-0.56

 JpaRepository

-0.56

POSITIVE LOGITS

 Kerajaan

0.45

 explosión

0.44

 Keuangan

0.43

 picioare

0.39

 Masyarakat

0.39

 palvel

0.38

 vklju

0.38

 sklo

0.37

 câte

0.37

 peč

0.37

Activations Density 0.018%

structured data types and their associated properties

foreign words in code

No Comments

No Known Activations