INDEX

Explanations

specific scientific terms and abbreviations related to biology and medicine

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

PGRP-LC / Prime / SP / advantage / active

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

 kaarangay

-0.89

AndEndTag

-0.80

 المعيارى

-0.77

GEBURTSDATUM

-0.74

rungsseite

-0.72

FunctionFlags

-0.71

ьаж

-0.67

Diweddarwch

-0.66

 дописавши

-0.64

 utafitiHapana

-0.63

POSITIVE LOGITS

 scorso

0.38

 charité

0.36

Referanser

0.35

onBackPressed

0.35

 peindre

0.35

RefreshToken

0.34

abetes

0.33

//</

0.33

 BitmapFactory

0.33

 pylab

0.32

Activations Density 0.159%

specific scientific terms and abbreviations related to biology and medicine

PGRP-LC / Prime / SP / advantage / active

No Comments

No Known Activations