INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

✨:

-0.72

ométrique

-0.50

 kern

-0.43

OfYear

-0.43

NSUInteger

-0.42

 relati

-0.42

orice

-0.42

xdf

-0.42

parseLong

-0.41

 themſelves

-0.41

POSITIVE LOGITS

WebVitals

0.80

TacToe

0.76

 springfox

0.70

Portale

0.68

 OFDb

0.68

dymyr

0.68

 disponibilités

0.67

 समीक्षाओं

0.64

 lccn

0.63

الدراسه

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.