INDEX

Explanations

technical terms related to research and scientific processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

StoryboardSegue

-0.91

hyrchwyd

-0.81

 queſta

-0.79

 estekak

-0.78

 Wicidata

-0.78

 AssemblyCompany

-0.71

IsMutable

-0.69

 kasarigan

-0.69

$_(

-0.68

writeFieldEnd

-0.68

POSITIVE LOGITS



0.35

cję

0.34

 sense

0.33

 شامل

0.33

 also

0.32

 beyond

0.31

non

0.30

 access

0.30

NotNil

0.30

 five

0.28

Activations Density 0.936%

technical terms related to research and scientific processes

No Comments

No Known Activations