INDEX

Explanations

structured data formats or code syntax elements

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

Code snippets or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

code blocks and syntax

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

 AttributeSet

-0.49

RefNanny

-0.48

invokeLater

-0.46

 churchyard

-0.46

 sows

-0.45

<eos>

-0.45

 Grimal

-0.44

 riuscito

-0.42

 myö

-0.42

htra

-0.42

POSITIVE LOGITS



0.76

 externi

0.71

rungsseite

0.71

 utafitiHapana

0.69

 estimés

0.68

 חיצוניים

0.66

 SwitchCompat

0.66

afficheront

0.66

Tikang

0.65

€)

0.65

Activations Density 0.292%

structured data formats or code syntax elements

Code snippets or mathematical expressions

code blocks and syntax

No Comments

No Known Activations