INDEX

Explanations

gene features, specifically focusing on coding exons, transcripts, and their regulatory elements

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

Coding sequences, genes, and translation

np_acts-logits-general · gemini-2.0-flash

gene coding regions translation

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

addCriterion

-0.52

 שוליים

-0.51

يميديا

-0.47

Jeografia

-0.46

+#+#

-0.46

 Inſ

-0.46

 rhestr

-0.45

 للمعارف

-0.44

asteroide

-0.44

 Chwiliwch

-0.43

POSITIVE LOGITS

 mRNA

0.51

mRNA

0.45

 gene

0.40

 Unmarshal

0.40

 transcribed

0.40

genes

0.39

 codon

0.38

 genes

0.38

 translated

0.37

Produkte

0.37

Activations Density 1.102%

gene features, specifically focusing on coding exons, transcripts, and their regulatory elements

Coding sequences, genes, and translation

gene coding regions translation

No Comments

No Known Activations