INDEX

Explanations

mentions of specific medical or research institutions

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

in languages other than English

np_acts-logits-general · gemini-2.0-flash

Hebrew and translation context

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

AddTagHelper

-0.45

rungsseite

-0.42

 kasarigan

-0.41

isbol

-0.40

xsl

-0.40

 Sault

-0.39

ecution

-0.37

 تضيفلها

-0.36

 unfavourable

-0.36

rull

-0.36

POSITIVE LOGITS

 للاسماء

0.54

RenderAtEndOf

0.52

הערות

0.50

 ChromeDriver

0.50

 חיצוניים

0.49

 OnTrigger

0.49

 FetchType

0.48

providedIn

0.47

encodeWith

0.45

findpost

0.45

Activations Density 0.015%

mentions of specific medical or research institutions

in languages other than English

Hebrew and translation context

No Comments

No Known Activations