INDEX

Explanations

terms and references related to laboratory materials and methods

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

catalog numbers and codes

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

جوايز

-0.36

 JpaRepository

-0.34

HostException

-0.33

AddTagHelper

-0.31

PBT

-0.31

 watered

-0.31

osene

-0.30

SpringRunner

-0.30

LLocation

-0.30

OBS

-0.29

POSITIVE LOGITS

Datuak

0.62

 noDo

0.54

 informée

0.52



0.52

 ujednoznacz

0.50

ⓧ

0.50

AISSEE

0.49

RTSN

0.48

WindowConstants

0.48

InitVars

0.48

Activations Density 0.033%

terms and references related to laboratory materials and methods

catalog numbers and codes

No Comments

No Known Activations