INDEX

Explanations

references to programming functions and their attributes

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

code and citations

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

transQ

-0.44

rawtypes

-0.40

 menge

-0.37

rspec

-0.36

[]>(

-0.35

ขน

-0.35

Dru

-0.34

 المعيارى

-0.34

jutnya

-0.34

rungsseite

-0.33

POSITIVE LOGITS

ISupport

0.60

 Савезне

0.58

 “…

0.52

 nahilalakip

0.50

 leſs

0.50

 Мексичка

0.49

ContentAsync

0.49

انتهای

0.48

Eſ

0.47

“…

0.47

Activations Density 0.029%

references to programming functions and their attributes

code and citations

No Comments

No Known Activations

references to programming functions and their attributes

code and citations

No Comments

No Known Activations