INDEX

Explanations

quantifiable metrics or counts

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

<start_of_turn> user

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

 Grüsse

-0.45

 initComponents

-0.44

SharedCtor

-0.43

 Infór

-0.41

 Portanto

-0.39

่านั้น

-0.39

DockStyle

-0.38

 debole

-0.38

 umgekehrt

-0.38

imarães

-0.37

POSITIVE LOGITS

')),

0.47

 docx

0.45

RTN

0.44

Hochspringen

0.43

 Hond

0.43

 paraf

0.41

Obrázky

0.41

plas

0.41

ยว

0.41

Ie

0.41

Activations Density 0.000%

quantifiable metrics or counts

<start_of_turn> user

No Comments

No Known Activations