INDEX

Explanations

specific medical or scientific terms and their implications

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

Tokens followed by parentheses

np_acts-logits-general · gemini-2.0-flash

opening parenthesis or quote

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 estekak

-1.00

writeFieldEnd

-0.91

存于互联网档案馆

-0.88

 للاسماء

-0.87

 AssemblyTitle

-0.85

 الرياضيه

-0.85

WithIOException

-0.84

 تانيه

-0.83

*/

-0.81

хьтан

-0.77

POSITIVE LOGITS

1.82

（

1.30

(=

1.15

("

1.07

 (“

1.06

 yani

1.03

（

1.03

1.02

1.00

 (‘

0.99

Activations Density 0.592%

specific medical or scientific terms and their implications

Tokens followed by parentheses

opening parenthesis or quote

No Comments

No Known Activations