INDEX

Explanations

elements related to technical specifications or programming syntax

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

Code-related or technical language

np_acts-logits-general · gemini-2.0-flash

optional bytes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SwitchCompat

-0.57

Personendaten

-0.56

 Paglinawan

-0.55

 مخطط

-0.54

Scénario

-0.54

 veau

-0.54

ProcessEvent

-0.53

 légumes

-0.53

 limón

-0.52

ソッド

-0.52

POSITIVE LOGITS

 resourceCulture

0.71

))))))))

0.68

 infine

0.67

 lastly

0.65

 Chwiliwch

0.64

 }}"></

0.60

 unknownFields

0.59

]")]

0.57

__*/

0.57

queryInterface

0.56

Activations Density 0.547%

elements related to technical specifications or programming syntax

Code-related or technical language

optional bytes

No Comments

No Known Activations