INDEX

Explanations

quantitative data related to measurements or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Numbers followed by a unit of measure

np_acts-logits-general · gemini-2.0-flash

numbers followed by units

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.78

 CreateTagHelper

-0.75

 ویکی‌پدی

-0.74

 يتيمه

-0.74

oredCriteria

-0.68

WriteTagHelper

-0.61

 وتسجيلات

-0.59

NameInMap

-0.59

AndEndTag

-0.59

ьаж

-0.57

POSITIVE LOGITS

 flat

0.48

 multi

0.47

flat

0.42

 French

0.41

 front

0.40

 Spanish

0.39

 Japan

0.39

Mrs

0.38

 Japanese

0.38

Activations Density 0.193%

quantitative data related to measurements or statistics

Numbers followed by a unit of measure

numbers followed by units

No Comments

No Known Activations