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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.81

 betweenstory

-0.76

Cyfarwyddwr

-0.70

󠁴

-0.69

 AssemblyCompany

-0.68

 <<<<<<<<<<<<<<

-0.67

 Administrativna

-0.66

windowFixed

-0.65

 IFTT

-0.63

ſicht

-0.63

POSITIVE LOGITS

SourceChecksum

0.68

TagHelper

0.33

তথ্যসূত্র

0.32

 caoutchouc

0.29

pè

0.26

">//

0.25

 RouterModule

0.23

 تانيه

0.23

 yrity

0.23

 pihaknya

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.