INDEX

Explanations

This neuron seems to activate on a variety of different subjects, but perhaps it is finding transitions or breaks in the text

oai_token-act-pair · gemini-2.0-flash

are

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

<bos>

-0.56

="">

-0.50

XmlIgnore

-0.49

\}.

-0.47

issau

-0.46

 totiž

-0.44

例文帳に追加

-0.44

 ارز

-0.42

щений

-0.41

ivant

-0.40

POSITIVE LOGITS

migrationBuilder

0.81

styleType

0.74

contentLoaded

0.73

 BoxFit

0.68

 protoimpl

0.65

دانشنامهٔ

0.63

NameInMap

0.62

BeginInit

0.61

EndInit

0.61

出版年

0.60

Activations Density 3.243%

This neuron seems to activate on a variety of different subjects, but perhaps it is finding transitions or breaks in the text

are

No Known Activations