INDEX

Explanations

specialized terms and brands in technology and scientific contexts

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

software and company names

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

 صوتيه

-0.76

 المعيارى

-0.74

 يتيمه

-0.73

 مشين

-0.71

rungsseite

-0.69

 createState

-0.68

 Administrativna

-0.67

Personendaten

-0.67

 kasarigan

-0.65

 consultato

-0.65

POSITIVE LOGITS

IAm

0.43

 ſche

0.43

 AstraZeneca

0.42

 TripAdvisor

0.41

 quæ

0.41

 Alamo

0.41

 souffle

0.41

 DisplayPort

0.40

 JoJo

0.40

 McMaster

0.40

Activations Density 0.090%

specialized terms and brands in technology and scientific contexts

software and company names

No Comments

No Known Activations