INDEX

Explanations

units of measurement and conversion-related terms

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

limited quantities or measurements

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

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

FunctionFlags

-0.72

 ویکی‌آمباردا

-0.54

orianCalendar

-0.48

LookAnd

-0.48

 CreateTagHelper

-0.48

 PopupWindow

-0.47

 Perugia

-0.47

RTEX

-0.46

 JpaRepository

-0.46

Datuak

-0.46

POSITIVE LOGITS

 limited

0.39

Limited

0.37

Diweddarwch

0.35

 Limited

0.35

limited

0.34

новништво

0.34

 siedz

0.33

tanleria

0.33

 limitada

0.33

 limitado

0.32

Activations Density 0.182%

units of measurement and conversion-related terms

limited quantities or measurements

No Comments

No Known Activations