INDEX

Explanations

references to geographic locations and specific organizations or entities

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

SIG constants

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 незавершена

-0.73

+#+

-0.67

ScopeManager

-0.66

 disambiguazione

-0.65

Personendaten

-0.63

 lenker

-0.60

 صوتيه

-0.60

出版年

-0.59

exitRule

-0.58

Tikang

-0.57

POSITIVE LOGITS

sihkan

0.43

giày

0.41

azzjoni

0.40

 amarelo

0.39

Dequeue

0.38

 Fitz

0.38

igreja

0.38

sepatu

0.37

 guerrero

0.37

 perang

0.37

Activations Density 0.376%

references to geographic locations and specific organizations or entities

SIG constants

No Comments

No Known Activations