INDEX

Explanations

references to microRNAs and their associated genes or factors

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

microRNA (miR) identifiers

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

 الرياضيه

-0.50

RepeatedField

-0.47

 tarko

-0.42

 femininas

-0.41

 vermelhas

-0.40

ärke

-0.40

 faptul

-0.39

賓

-0.38

żyw

-0.38

GTCX

-0.37

POSITIVE LOGITS

miR

0.96

 miRNA

0.92

miR

0.90

 miRNAs

0.83

meralda

0.45

verwijspagina

0.44

Démographie

0.42

makeConstraints

0.41

EDTA

0.41

ünchen

0.40

Activations Density 0.093%

references to microRNAs and their associated genes or factors

microRNA (miR) identifiers

No Comments

No Known Activations