INDEX

Explanations

specific numerical or mathematical expressions and sequences

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

Numbers within identifiers or codes

np_acts-logits-general · gemini-2.0-flash

numbers and identifiers

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

migrationBuilder

-0.71

 Exacts

-0.66

ละ

-0.60

astéro

-0.60

ngdoc

-0.58

encodeWith

-0.57

dieron

-0.57

förm

-0.56

واع

-0.56

Насе

-0.56

POSITIVE LOGITS

 ontstaan

0.46

 issued

0.45

Growing

0.45

0.43

IonicModule

0.42

خصة

0.42

כול

0.42

 newOwner

0.42

 renfer

0.42

Activations Density 1.083%

specific numerical or mathematical expressions and sequences

Numbers within identifiers or codes

numbers and identifiers

No Comments

No Known Activations