INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

tagHelperRunner

-0.65

setVerticalGroup

-0.64

 consultato

-0.56

Lähteet

-0.56

 incomplète

-0.54

 protoimpl

-0.52

ⓧ

-0.50

Искәрмәләр

-0.50

ExtendWith

-0.48

 ExecuteAsync

-0.48

POSITIVE LOGITS

 незавершена

2.81

protoimpl

2.13

 стаття

2.02

 tartalomajánló

1.14

 Biografie

0.64

Denne

0.61

 HttpNotFound

0.59

графії

0.56

 سكانية

0.55

دانشنامهٔ

0.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.