INDEX

Explanations

terms related to specific locations and governance structures

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

geographical and political entities

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

Carriera

-0.56

Gön

-0.53

TagHelper

-0.52

WriteLiteral

-0.50



-0.48

WriteTagHelper

-0.48

 Audiodateien

-0.47

 ModelExpression

-0.47

Estima

-0.46

isContained

-0.46

POSITIVE LOGITS

Portály

0.47

bukaan

0.41

 paesi

0.40

édrale

0.40

ederal

0.40

 traseira

0.40

jestic

0.39

esercito

0.39

president

0.38

 wensen

0.38

Activations Density 0.155%

terms related to specific locations and governance structures

geographical and political entities

No Comments

No Known Activations