INDEX

Explanations

conjunctions that indicate additional components or quantities

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

plus followed by numbers or nouns

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

UserScript

-0.48

 volant

-0.46

ScopeManager

-0.45

 Houſe

-0.44

ArgumentParser

-0.43

 airfoil

-0.42

 houſe

-0.42

WriteBarrier

-0.41

 VIAF

-0.41

 ModelRenderer

-0.40

POSITIVE LOGITS

 plus

1.31

 плюс

1.03

plus

0.93

 ditambah

0.82

 PLUS

0.71

＋

0.68

 nebst

0.68

 minus

0.67

再加上

0.67

$+

0.65

Activations Density 0.009%

conjunctions that indicate additional components or quantities

plus followed by numbers or nouns

No Comments

No Known Activations