INDEX

Explanations

pharmaceutical or biochemical terms related to neurotransmitter analysis

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

references to analytical methods and specific chemical compounds

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

dopamine and serotonin functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Paglinawan

-0.66

localctx

-0.65

 debtor

-0.58

 debtors

-0.56

Conven

-0.56

 Westmoreland

-0.56

Personendaten

-0.56

 loaf

-0.56

 visco

-0.55

وصلات

-0.55

POSITIVE LOGITS

 serotonin

0.93

otonin

0.77

Dop

0.69

 dopamine

0.67

Dop

0.67

 tyrosine

0.64

dop

0.61

 Parkinson

0.60

dop

0.58

runApp

0.58

Activations Density 0.306%

pharmaceutical or biochemical terms related to neurotransmitter analysis

references to analytical methods and specific chemical compounds

dopamine and serotonin functions

No Comments

No Known Activations