INDEX

Explanations

mentions of rivers and related geographical features

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

following "River" or "river"

np_acts-logits-general · gemini-2.0-flash

river geographical context

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

Geplaatst

-0.71

+#+

-0.71

InputBorder

-0.67

ftagPool

-0.64

WithMany

-0.63

 Exacts

-0.62

<()>

-0.60

 &___

-0.59

trui

-0.59

Дереккөздер

-0.59

POSITIVE LOGITS

bed

0.76

ine

0.72

bank

0.72

banks

0.72

 valley

0.71

 basin

0.66

bend

0.65

front

0.64

 Basin

0.62

 estuary

0.61

Activations Density 0.085%

mentions of rivers and related geographical features

following "River" or "river"

river geographical context

No Comments

No Known Activations