INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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



-1.05

 متعلقه

-1.04

tagHelperRunner

-1.02

 nahilalakip

-1.01

DockStyle

-1.01

 typelib

-0.94

存于互联网档案馆

-0.92

 pinulongan

-0.91

IGraphics

-0.87

AnchorStyles

-0.84

POSITIVE LOGITS

↵↵

0.89

The

0.81

The

0.69

0.59

↵

0.53

 Additionally

0.51

なお

0.50

Additionally

0.50

0.49

 Both

0.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.