INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

Symfony

-0.57

LabelTagHelper

-0.57

tagHelperRunner

-0.55

UnknownFieldSet

-0.55

 dadas

-0.53

FontWeight

-0.52

 supérieures

-0.51

 illustrazione

-0.50

 noDo

-0.50

AfterClass

-0.50

POSITIVE LOGITS

 وتسجيلات

0.79

ChildScrollView

0.75

примеча

0.68

]")]

0.68

 infide

0.68

 arşivlendi

0.66

InstanceState

0.64

DockStyle

0.62

 imageNamed

0.61

aarrggbb

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.