INDEX

Explanations

technical terms and measurements related to imaging and biological analysis

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

Values being measured or assessed

np_acts-logits-general · gemini-2.0-flash

performing measurements and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

SequentialGroup

-0.88

 Majefty

-0.83

GEBURTSDATUM

-0.81

 Houſe

-0.77

 pinulongan

-0.77

 itſelf

-0.77

 ſche

-0.77

 Monfieur

-0.75

ConstraintMaker

-0.75

 Jefus

-0.74

POSITIVE LOGITS

 were

0.67

was

0.66

 consisted

0.65

 ensured

0.53

 underwent

0.49

 obtained

0.46

 remained

0.45

 uniformly

0.45

 immediately

0.45

 subsequently

0.45

Activations Density 4.999%

technical terms and measurements related to imaging and biological analysis

Values being measured or assessed

performing measurements and analysis

No Comments

No Known Activations

technical terms and measurements related to imaging and biological analysis

Values being measured or assessed

performing measurements and analysis

No Comments

No Known Activations