INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ьаж

-0.68

AddTagHelper

-0.66

 CreateTagHelper

-0.61

 <<<<<<<<<<<<<<

-0.61

tagHelperRunner

-0.59

Personensuche

-0.57

 autorytatywna

-0.53

 Administrativna

-0.52

archiviato

-0.50

BeginInit

-0.50

POSITIVE LOGITS

majánló

0.42

 Monfieur

0.39

 optimise

0.39

 Houſe

0.38

 heroic

0.38

 sermons

0.38

 entrepreneurial

0.38

 shoppers

0.38

 heroes

0.37

 racist

0.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.