INDEX

Explanations

genes and their associated markers or identifiers

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

Tokens followed by parentheses

np_acts-logits-general · gemini-2.0-flash

mathematical expressions and acronyms

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

erequisite

-0.34

ientôt

-0.34

correct

-0.30

 teka

-0.29

 према

-0.29

ViewFeatures

-0.29

 așa

-0.29

écial

-0.28

 خبری

-0.28

 potem

-0.28

POSITIVE LOGITS

 CreateTagHelper

0.73

 invokingState

0.62

 ब्रेकडाउन

0.59

SourceChecksum

0.57

uxxxx

0.56

RTDA

0.54

EDEFAULT

0.54

点此举报

0.54

الحياه

0.53

aarrggbb

0.53

Activations Density 1.630%

genes and their associated markers or identifiers

Tokens followed by parentheses

mathematical expressions and acronyms

No Comments

No Known Activations

genes and their associated markers or identifiers

Tokens followed by parentheses

mathematical expressions and acronyms

No Comments

No Known Activations