INDEX

Explanations

expressions of possession and personal relationships

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

my or I statement

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

 muuta

-0.48

 dormitórios

-0.43

 enää

-0.43

 tapaht

-0.42

 zvíř

-0.41

 vastaan

-0.41

 sää

-0.41

 elä

-0.41

accompag

-0.40

 huom

-0.40

POSITIVE LOGITS

ParallelGroup

0.65

tagHelperRunner

0.60

 للاسماء

0.54

saraba

0.49

 Мексичка

0.46

Sólo

0.43

новништво

0.41

VYMaps

0.40

atschappij

0.40

 Langen

0.40

Activations Density 0.095%

expressions of possession and personal relationships

my or I statement

No Comments

No Known Activations

expressions of possession and personal relationships

my or I statement

No Comments

No Known Activations