INDEX

Explanations

specific numerical or technical data references

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

Appears before identifiers/names

np_acts-logits-general · gemini-2.0-flash

identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ंदीखरीदारी

-0.75

 AttributeSet

-0.54

uxxxx

-0.52

 surla

-0.51

xase

-0.51

 ModelExpression

-0.50

 resourceCulture

-0.50

 Wikimedijinoj

-0.49

WriteTagHelper

-0.48

TypedDataSet

-0.48

POSITIVE LOGITS

Aholisi

0.50

awtextra

0.47

withIdentifier

0.40

Grü

0.40

 שוליים

0.38

timb

0.37

 Reinh

0.36

pad

0.35

ograph

0.34

zip

0.34

Activations Density 0.387%

specific numerical or technical data references

Appears before identifiers/names

identifiers or codes

No Comments

No Known Activations