INDEX

Explanations

structured sections of scientific papers, particularly those detailing methods, results, and discussions

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

Text preceding section numbers

np_acts-logits-general · gemini-2.0-flash

section headings and numbers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.47

 También

-0.44

if

-0.43

ул

-0.43

Nope

-0.43

 somewhere

-0.43

 нем

-0.42

جغرافيا

-0.42

 jist

-0.41

magine

-0.41

POSITIVE LOGITS

tvguidetime

0.88

ंदीखरीदारी

0.84

 utafitiHapana

0.83

 estimés

0.81

RectangleBorder

0.75

 }}"></

0.72

 Chwiliwch

0.71

\{\\

0.70

 doInBackground

0.70

 BoxFit

0.69

Activations Density 0.223%

structured sections of scientific papers, particularly those detailing methods, results, and discussions

Text preceding section numbers

section headings and numbers

No Comments

No Known Activations