INDEX

Explanations

terms related to artificial neural networks and their structure

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

neural networks and their architecture

np_acts-logits-general · gemini-2.0-flash

neural network architecture

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Demografia

-0.62

UnknownFields

-0.59

:✨

-0.58

ัติ

-0.55

RetentionPolicy

-0.54

 GALLERY

-0.54

 gallery

-0.53

adpleegd

-0.52

 INSTITUTION

-0.51

 Waray

-0.51

POSITIVE LOGITS

 transférez

0.75

 neurons

0.68

 neuron

0.66

 networks

0.64

 network

0.61

 cell

0.60

enderror

0.59

 neur

0.59

 neural

0.58

 Neuron

0.58

Activations Density 0.280%

terms related to artificial neural networks and their structure

neural networks and their architecture

neural network architecture

No Comments

No Known Activations