INDEX

Explanations

measurements and dimensions

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

Units of measurement followed by dimensions

np_acts-logits-general · gemini-2.0-flash

measurements of size and duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

TagMode

-0.73

LabelTagHelper

-0.58

 henvisninger

-0.51

出版年

-0.51

PropertyGroup

-0.49

RTSC

-0.48

 AssemblyCulture

-0.48

期刊论文

-0.48

TintMode

-0.48

more

-0.47

POSITIVE LOGITS

 wide

1.59

 tall

1.54

 long

1.43

tall

1.23

wide

1.14

 deep

1.08

 Wide

1.08

 WIDE

1.07

 thick

1.05

 Tall

1.04

Activations Density 0.225%

measurements and dimensions

Units of measurement followed by dimensions

measurements of size and duration

No Comments

No Known Activations