INDEX

Explanations

dimensions and weight metrics

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

height and weight

np_acts-logits-general · gemini-2.0-flash

height and build measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

లాలు

-0.53

 gedrag

-0.49

docx

-0.49

SBATCH

-0.48

ilarang

-0.47

 насеље

-0.47

 kasarigan

-0.47

 nød

-0.45

modb

-0.45

ethene

-0.45

POSITIVE LOGITS

 tall

1.58

 taller

1.52

 height

1.43

 tallest

1.34

Tall

1.26

tall

1.25

 Height

1.25

 Tall

1.23

 HEIGHT

1.22

Height

1.20

Activations Density 0.416%

dimensions and weight metrics

height and weight

height and build measurements

No Comments

No Known Activations