INDEX

Explanations

structured data types and documentation comments

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

Tokens followed by "@" or "[@" or ":@"

np_acts-logits-general · gemini-2.0-flash

documentation tags and citations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jefus

-0.73

 XNUMX

-0.63

Parcelize

-0.58

 مؤرشف

-0.57

říklad

-0.57

 itſelf

-0.56

 fubject

-0.56

Efq

-0.55

ſelf

-0.54

 houſe

-0.52

POSITIVE LOGITS

3.32

3.00

(@

2.16

(@

2.08

,@

2.06

"@

1.88

=@

1.86

'@

1.86

/@

1.83

.@

1.83

Activations Density 0.521%

structured data types and documentation comments

Tokens followed by "@" or "[@" or ":@"

documentation tags and citations

No Comments

No Known Activations