INDEX

Explanations

numerical values related to measurements or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

212 or 2 sequences

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

GEBURTSDATUM

-0.83

Tikang

-0.79

 autorytatywna

-0.74

SourceChecksum

-0.67

WriteTagHelper

-0.63

Autoritní

-0.60

Personensuche

-0.59

 defaultstate

-0.56

elemField

-0.54

Билгалдахарш

-0.54

POSITIVE LOGITS

Życiorys

0.43

SAS

0.38

dll

0.36

Tori

0.35

SAS

0.35

CDC

0.35

valdi

0.34

 dàng

0.34

 Informasi

0.33

bollah

0.32

Activations Density 0.031%

numerical values related to measurements or statistics

212 or 2 sequences

No Comments

No Known Activations