INDEX

Explanations

terms and concepts related to biochemical processes and neurophysiology

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

brain structures and responses

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

تقاوى

-0.35

 push

-0.32

 stos

-0.30

 Push

-0.29

Push

-0.29

esModule

-0.27

 form

-0.27

openzeppelin

-0.27

res

-0.27

le

-0.27

POSITIVE LOGITS

 defaultstate

0.76

webElementXpaths

0.70

httphttps

0.68

tvguidetime

0.68

NameInMap

0.65

ſelf

0.65

WebElementEntity

0.65

 disambiguazione

0.63

gdala

0.63

CppMethod

0.63

Activations Density 0.136%

terms and concepts related to biochemical processes and neurophysiology

brain structures and responses

No Comments

No Known Activations