INDEX

Explanations

elements of numerical data and associated classifications or identifiers

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

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

jsdelivr

-0.53

Hauptartikel

-0.48

 kaarangay

-0.47

ParallelGroup

-0.44

reg

-0.43

al

-0.43

 الحره

-0.43

subsubsection

-0.42

ercice

-0.41

 وتسجيلات

-0.41

POSITIVE LOGITS

ContentAsync

0.78

PerformLayout

0.74

rawDesc

0.73

 تضيفلها

0.67

 onAnimation

0.67

ंदीखरीदारी

0.64

InstanceState

0.64

 TextInputType

0.62

MeasureSpec

0.62

MemoryWarning

0.59

Activations Density 0.995%

elements of numerical data and associated classifications or identifiers

No Comments

No Known Activations