INDEX

Explanations

elements related to scientific studies and methodologies

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

preceding academic terms or study types

np_acts-logits-general · gemini-2.0-flash

research study components

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

才會

-0.60

才可以

-0.55

才会

-0.54

 Վերցված

-0.54

 adev

-0.54

才能

-0.53

PHONY

-0.52

Dónde

-0.52

 competitive

-0.51

 wait

-0.51

POSITIVE LOGITS

ScopeManager

0.67

 виправивши

0.58

 utafitiHapana

0.58

Попис

0.56

 uwagę

0.56

 doté

0.53

 hails

0.52

 mappa

0.52

SBATCH

0.51

 stammt

0.50

Activations Density 0.606%

elements related to scientific studies and methodologies

preceding academic terms or study types

research study components

No Comments

No Known Activations