INDEX

Explanations

code related to message updates and sizes, potentially in a hardware or driver context

oai_token-act-pair · gemini-2.0-flash

num

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/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.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

num

-1.83

num

-1.74

Num

-1.59

Num

-1.45

NUM

-1.31

NUM

-1.18

 getNum

-1.08

getNum

-1.02

<bos>

-1.01

nums

-0.96

POSITIVE LOGITS

tagHelperRunner

0.62

principalTable

0.60

multirow

0.54

numerusform

0.54

Personensuche

0.49

englanniksi

0.47

EndContext

0.46

تقاوى

0.45

GEBURTS

0.44

inhua

0.43

Activations Density 4.563%

code related to message updates and sizes, potentially in a hardware or driver context

num

No Comments

No Known Activations