INDEX

Explanations

references to geographical locations and Canadian jurisdictions

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

"British" followed by "Columbia"

np_acts-logits-general · gemini-2.0-flash

British Columbia

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

DoubleQuotes

-0.74

 Waray

-0.71

RectangleBorder

-0.67

WithMany

-0.66

醐

-0.62

ContentAsync

-0.58

ngrx

-0.58

曖昧さ回避

-0.57

ёх

-0.56

 CreateTagHelper

-0.56

POSITIVE LOGITS

stateMutability

0.63

AB

0.50

 صالح

0.49

AB

0.49

ৎ

0.48

MLA

0.47

 Еще

0.47

 stabilized

0.47

odc

0.46

localctx

0.46

Activations Density 0.053%

references to geographical locations and Canadian jurisdictions

"British" followed by "Columbia"

British Columbia

No Comments

No Known Activations