INDEX

Explanations

codes and related numerical identifiers

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

"code" paired with hexadecimal values

np_acts-logits-general · gemini-2.0-flash

code : hex identifier

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 viewWillAppear

-0.43

Datuak

-0.38

DotNetBar

-0.37

 férias

-0.37

viewWillAppear

-0.36

(!(

-0.35

+:

-0.35

-\\

-0.34

ster

-0.34

 pleinement

-0.34

POSITIVE LOGITS

 code

2.63

 Code

2.48

Code

2.39

code

2.30

 CODE

2.23

 codes

2.19

 Codes

2.14

CODE

2.06

Codes

1.91

 getCode

1.84

Activations Density 0.186%

codes and related numerical identifiers

"code" paired with hexadecimal values

code : hex identifier

No Comments

No Known Activations

codes and related numerical identifiers

"code" paired with hexadecimal values

code : hex identifier

No Comments

No Known Activations