INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 defaultstate

-0.82



-0.64

qld

-0.61

//</

-0.59

 Queensland

-0.59

PyExc

-0.59

QLD

-0.58

 Mackay

-0.58

orteur

-0.58

creativecommons

-0.56

POSITIVE LOGITS

 NYPD

0.79

NJ

0.74

NJ

0.73

 Rockland

0.73

 Westchester

0.71

 borough

0.70

 Newark

0.68

 Connecticut

0.68

 Borough

0.66

 Staten

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.