INDEX

Explanations

numerical values associated with scores or metrics

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

Numbers within mathematical or code-related contexts

np_acts-logits-general · gemini-2.0-flash

specific scientific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Jeografia

-0.73

DialogContent

-0.67

 AsyncTask

-0.66

UrlEncoded

-0.66

 WebDriverWait

-0.66

TintMode

-0.65

AndEndTag

-0.65

Бахар

-0.63

 المكتبه

-0.61

 كومونز

-0.60

POSITIVE LOGITS

 zoomed

0.55

 Maat

0.54

 resized

0.52

Vey

0.52

 cropped

0.51

ifflin

0.49

 Uniti

0.49

 decret

0.48

 rectangle

0.47

 enlarged

0.47

Activations Density 0.117%

numerical values associated with scores or metrics

Numbers within mathematical or code-related contexts

specific scientific terms

No Comments

No Known Activations