INDEX

Explanations

verbs related to actions and expressions

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

verbs followed by names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

RenderAtEndOf

-0.66

GEBURTSDATUM

-0.62

endphp

-0.57

ंदीखरीदारी

-0.57

 AssemblyTitle

-0.56



-0.54

XmlAccessorType

-0.54

 للاسماء

-0.52

leyin

-0.50

uxxxx

-0.49

POSITIVE LOGITS

 astore

0.42

DrawerToggle

0.36

 chủ

0.32

汁

0.29

 Audiodateien

0.29

 Agre

0.29

 choice

0.28

authorised

0.28

ategorias

0.28

সং

0.28

Activations Density 0.084%

verbs related to actions and expressions

verbs followed by names

No Comments

No Known Activations