INDEX

Explanations

words and phrases related to professions and careers, particularly in political and academic contexts, and sometimes relating to time and seasonality

oai_token-act-pair · gemini-2.0-flash

Year

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 year

-0.96

year

-0.81

 years

-0.78

 Year

-0.76

 año

-0.75

Year

-0.74

getYear

-0.73

 YEAR

-0.73

 année

-0.72

 Jahr

-0.69

POSITIVE LOGITS

 consultato

0.68

 weekly

0.67

 חיצוניים

0.66

weekly

0.61

SequentialGroup

0.60

 riuscito

0.59

NOPQRST

0.59

 Weekly

0.59

 hebdomada

0.56

 Сегодня

0.55

Activations Density 6.144%

words and phrases related to professions and careers, particularly in political and academic contexts, and sometimes relating to time and seasonality

Year

No Known Activations