INDEX

Explanations

numerical data or statistics within the text

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

able to

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

ArrowToggle

-0.38

jenost

-0.33

ésultat

-0.32

AndroidJUnit

-0.31

 Fried

-0.30

analisi

-0.29

 veřej

-0.29

associazione

-0.28

pektive

-0.28

 vulné

-0.28

POSITIVE LOGITS

Efq

0.69

 ſind

0.64

 ſein

0.61

$_(

0.60

 Houſe

0.59

 ſei

0.59

$_"

0.59

 queſta

0.59

 betweenstory

0.58

 zwiſchen

0.58

Activations Density 0.039%

numerical data or statistics within the text

able to

No Comments

No Known Activations