INDEX

Explanations

expressions of gratitude and positive feedback

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

Text following punctuation (.,?,!)

np_acts-logits-general · gemini-2.0-flash

sentence ending punctuation

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

 BitmapFactory

-0.55

Numerology

-0.54

Opinion

-0.53

BufferException

-0.53

momix

-0.52

GetObject

-0.52

initComponents

-0.52

freopen

-0.51

⎨

-0.50

edicated

-0.50

POSITIVE LOGITS

Werde

0.80

 hadn

0.65

 interestingly

0.62

apparently

0.60

 Gonna

0.60

 luckily

0.60

WebServlet

0.59

 justement

0.59

 Apparently

0.59

 ſhould

0.59

Activations Density 0.134%

expressions of gratitude and positive feedback

Text following punctuation (.,?,!)

sentence ending punctuation

No Comments

No Known Activations