INDEX

Explanations

terms related to protein tagging and purification methodologies

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

protein tags and labels

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

책

-0.45

ogram

-0.42

 Buon

-0.41

InUse

-0.41

筋

-0.40

modelle

-0.39

 doInBackground

-0.39

 Frick

-0.39

'][]

-0.39

 stroke

-0.39

POSITIVE LOGITS

ьаж

0.68

OGND

0.49

 Италијани

0.49

yarnpkg

0.48

PerformLayout

0.46

GFP

0.44

HasForeignKey

0.43

RTLD

0.43

 CreateTagHelper

0.43

 Мексичка

0.41

Activations Density 0.255%

terms related to protein tagging and purification methodologies

protein tags and labels

No Comments

No Known Activations