INDEX

Explanations

technical terms or specialized jargon in scientific or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

RectangleBorder

-1.10

ViewImports

-0.78

OGND

-0.78

HomeAsUpEnabled

-0.76

AnchorStyles

-0.73

archiviato

-0.73

 FontWeight

-0.72

ScopeManager

-0.71

سطس

-0.71

ChildIndex

-0.70

POSITIVE LOGITS

 localVar

1.95

localVar

1.14

 protoimpl

1.00

iVar

0.99

uParam

0.93

 iParam

0.87

 paramInt

0.85

 pulumi

0.83

iParam

0.80

ɵɵ

0.71

Activations Density 0.017%

technical terms or specialized jargon in scientific or mathematical contexts

No Comments

No Known Activations