INDEX

Explanations

references to geographical locations or administrative divisions

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

of the

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

IUrlHelper

-0.44

Derbyniad

-0.43

cetines

-0.41

Erfolge

-0.41

軋

-0.39

 kaarangay

-0.38

 predictable

-0.38

 nahilalakip

-0.38

GRANTED

-0.38

 manualidades

-0.37

POSITIVE LOGITS

enumii

0.54

enumi

0.53

Personendaten

0.50

Javadoc

0.44

ubri

0.43

bootstrapcdn

0.41

 Oscar

0.40

entru

0.40

bkz

0.40

aughter

0.40

Activations Density 0.064%

references to geographical locations or administrative divisions

of the

No Comments

No Known Activations