INDEX

Explanations

names and other identifiers related to individuals or entities

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

Japanese names and phrases

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

 témoig

-0.75

 ſind

-0.74

 ſei

-0.71

ロウィン

-0.68

RegressionTest

-0.67

 ſche

-0.65

 ſch

-0.62

 ſever

-0.62

ſelf

-0.62

AddHtmlAttribute

-0.61

POSITIVE LOGITS



0.41

 nonUne

0.39

cũ

0.38

 Cancelar

0.37

baliknya

0.34

 kayu

0.34

Funding

0.33

Personensuche

0.33

Sede

0.33

 semoga

0.32

Activations Density 0.031%

names and other identifiers related to individuals or entities

Japanese names and phrases

No Comments

No Known Activations