INDEX

Explanations

specific product promotions and offers

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

equations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DIPSETTING

-0.44

NullCheck

-0.43

>//

-0.41

 surla

-0.36

 uParam

-0.36

 Autorizaciones

-0.35

PLANATION

-0.33

bootstrapcdn

-0.33

endmodule

-0.33

ंदीखरीदारी

-0.33

POSITIVE LOGITS

ChildScrollView

0.61

 незавершена

0.60

webElementXpaths

0.60

 ſind

0.57

 Pardavimas

0.50

قایناق‌لار

0.50

tvguidetime

0.49

mios

0.48

 geox

0.48

 crochê

0.48

Activations Density 0.054%

specific product promotions and offers

equations and references

No Comments

No Known Activations