INDEX

Explanations

terms related to neurology and neurological sciences

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

the prefix "neuro" and its related fields

np_acts-logits-general · gemini-2.0-flash

neuroscience and neural networks

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

flashdata

-0.58

 umano

-0.54

 مشين

-0.53

InSection

-0.53

agie

-0.48

 Basta

-0.47

WriteTagHelper

-0.47

 géant

-0.46

::_('

-0.46

Manfaat

-0.46

POSITIVE LOGITS

 neuro

0.67

 Neuro

0.64

 Neural

0.63

">//

0.60

 neural

0.60

 uLocal

0.58

Neural

0.58

География

0.58

WhereInput

0.57

Neuro

0.56

Activations Density 0.146%

terms related to neurology and neurological sciences

the prefix "neuro" and its related fields

neuroscience and neural networks

No Comments

No Known Activations