INDEX

Explanations

scientific concepts related to neurotransmitter levels and methodologies for their analysis

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

Neurotransmitters and their abbreviations

np_acts-logits-general · gemini-2.0-flash

serotonin and dopamine neurons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

localctx

-0.55

 visco

-0.54

HSS

-0.54

وصلات

-0.54

 Apos

-0.54

 Patro

-0.53

Lyd

-0.50

 Conſ

-0.49

 Gators

-0.49

Mud

-0.48

POSITIVE LOGITS

 serotonin

0.88

otonin

0.76

 dopamine

0.75

dop

0.68

Dop

0.67

Dop

0.65

ParallelGroup

0.64

 tyrosine

0.60

$_['

0.59

printStackTrace

0.59

Activations Density 0.607%

scientific concepts related to neurotransmitter levels and methodologies for their analysis

Neurotransmitters and their abbreviations

serotonin and dopamine neurons

No Comments

No Known Activations