INDEX

Explanations

The neuron activates on the structure or formatting of documents, including numbering, introductions, and common thanking phrases.

oai_token-act-pair · gemini-2.0-flash

period punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

contentLoaded

-1.21

 Himo

-1.19

ReusableCell

-1.18

protoimpl

-1.17

 Савезне

-1.16

GEBURTSDATUM

-1.13

 kaarangay

-1.10

Personensuche

-1.09

 Мексичка

-1.09

LookAnd

-1.09

POSITIVE LOGITS

and

0.79

0.77

in

0.75

the

0.71

0.70

0.69

↵↵

0.69

0.68

an

0.66

Activations Density 3.709%

The neuron activates on the structure or formatting of documents, including numbering, introductions, and common thanking phrases.

period punctuation

No Comments

No Known Activations