INDEX

Explanations

key terms and concepts associated with scientific and technical accuracy

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

Definitions or explanations of terms

np_acts-logits-general · gemini-2.0-flash

defines or explains concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

getColumnIndex

-0.49

IsUnicode

-0.39

しかも

-0.39

MigrationBuilder

-0.38

__(/*!

-0.37

 newBuilder

-0.36

PyExc

-0.35

 spied

-0.35

jsxFileName

-0.35

ьаж

-0.34

POSITIVE LOGITS

 refers

0.80

 disambiguazione

0.72

 defined

0.71

 istilah

0.69

 term

0.69

 polega

0.69

 Defined

0.65

 basically

0.64

defined

0.63

 inaczej

0.63

Activations Density 0.597%

key terms and concepts associated with scientific and technical accuracy

Definitions or explanations of terms

defines or explains concepts

No Comments

No Known Activations