INDEX

Explanations

place names and geographic locations

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

countries and regions

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

 виправивши

-0.42

 pulumi

-0.36

ent

-0.35

 мәкал

-0.35

әрмәләр

-0.33

feature

-0.33

ynb

-0.32

Eis

-0.32

={`/

-0.32

 beam

-0.31

POSITIVE LOGITS

 snippetHide

0.51

CloseOperation

0.50

يكب

0.48

istoitu

0.46

 peggio

0.46

 autorytatywna

0.46

provin

0.46

setVerticalGroup

0.45

 enví

0.44

ureusement

0.44

Activations Density 0.031%

place names and geographic locations

countries and regions

No Comments

No Known Activations