INDEX

Explanations

technical terms and references related to scientific studies, particularly in biology and medicine

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

Followed by a lowercase letter

np_acts-logits-general · gemini-2.0-flash

§, portions, ™, motor, server, identifiable

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Rujuakan

-0.51

IBOutlet

-0.46

ulongan

-0.44

WriteTagHelper

-0.44

fflush

-0.44

 incentiv

-0.44

 kasarigan

-0.43

 linkovi

-0.43

 xung

-0.43

phology

-0.41

POSITIVE LOGITS

 regulador

0.37

 dramatique

0.36

 صوتيه

0.35

 transfieras

0.35

Gön

0.35

 supplémentaires

0.34

 Concerning

0.34

 Tampoco

0.33

 Regarding

0.33

 additionally

0.33

Activations Density 0.952%

technical terms and references related to scientific studies, particularly in biology and medicine

Followed by a lowercase letter

§, portions, ™, motor, server, identifiable

No Comments

No Known Activations