INDEX

Explanations

references to Apache and related organizational structures or formats

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Code, imports, and version numbers

np_acts-logits-general · gemini-2.0-flash

technical identifiers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 AssemblyCulture

-0.49

apimachinery

-0.47

jamientos

-0.47

CloseOperation

-0.45

tæ

-0.42

 agresión

-0.41

martre

-0.40

 detención

-0.39

 vacunación

-0.39

 disambiguazione

-0.39

POSITIVE LOGITS

 betweenstory

0.56

 iota

0.52

Gig

0.48

 Emerald

0.47

:");

0.47

 Elder

0.45

Selfer

0.45

startup

0.45

 Cyber

0.45

enumi

0.44

Activations Density 0.339%

references to Apache and related organizational structures or formats

Code, imports, and version numbers

technical identifiers

No Known Activations