INDEX

Explanations

words related to businesses, particularly restaurants, cafes, shops, and banks

oai_token-act-pair · gemini-2.0-flash

Food service establishments

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

bar

-0.65

 restaurant

-0.65

 bars

-0.60

 Grill

-0.59

 Vikipedi

-0.58

 Restaurant

-0.58

msgTypes

-0.57

 restaurants

-0.56

 diner

-0.56

 restaur

-0.56

POSITIVE LOGITS

ftagPool

0.69

HideFlags

0.66

giarism

0.62

الحياه

0.61

 Jefus

0.60

hringer

0.58

 nahilalakip

0.58

StoryboardSegue

0.58

 betweenstory

0.57

aaral

0.55

Activations Density 2.907%

words related to businesses, particularly restaurants, cafes, shops, and banks

Food service establishments

No Comments

No Known Activations