INDEX

Explanations

references to the "face value" of documents or claims

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

on its face / nominal

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

 للمعارف

-0.75

WebElementEntity

-0.69

RTDA

-0.67

rungsseite

-0.66

 kasarigan

-0.66

NameInMap

-0.64

AccessorTable

-0.63

MemoryWarning

-0.63

 otomatig

-0.63

 Numerade

-0.62

POSITIVE LOGITS

 mệnh

0.30

Extinguishing

0.28

ध

0.26

 pekerja

0.25

 номина

0.24

 sociais

0.24

 peito

0.24

 retail

0.24

 syke

0.24

czo

0.23

Activations Density 0.072%

references to the "face value" of documents or claims

on its face / nominal

No Comments

No Known Activations