INDEX

Explanations

technical specifications and settings for display parameters

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

Tokens before numbers in resolutions

np_acts-logits-general · gemini-2.0-flash

video resolution dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

gameserver

-0.64

IntoConstraints

-0.60

 समीक्षाओं

-0.53

'/',

-0.52

 utafitiHapana

-0.51

 realizes

-0.50

Hochspringen

-0.49

 fronte

-0.49

 estimés

-0.49

sima

-0.48

POSITIVE LOGITS

 resolutions

0.65

 Resolution

0.62

WithMany

0.60

 resolution

0.60

 Resolutions

0.59

Източници

0.58

Resolution

0.57

 resolución

0.56

yntaxException

0.56

offsetWidth

0.56

Activations Density 0.151%

technical specifications and settings for display parameters

Tokens before numbers in resolutions

video resolution dimensions

No Comments

No Known Activations