INDEX

Explanations

information related to clinical trials and regulatory processes

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

preceding/following auxiliary verbs

np_acts-logits-general · gemini-2.0-flash

recently applied verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 becomes

-0.79

 होती

-0.74

becomes

-0.73

 होता

-0.71

 होते

-0.67

 gets

-0.65

 goes

-0.62

 takes

-0.59

 develops

-0.58

 emerges

-0.57

POSITIVE LOGITS

 recently

1.36

recently

1.26

 Recently

1.14

Recently

1.13

 đã

1.13

 telah

1.12

 recentemente

1.02

 récente

0.99

 recientemente

0.98

 hasn

0.97

Activations Density 1.199%

information related to clinical trials and regulatory processes

preceding/following auxiliary verbs

recently applied verbs

No Comments

No Known Activations