INDEX

Explanations

mentions of Google and its products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

es

-0.72

 FormsModule

-0.68

-0.62

<%=

-0.59

 Verge

-0.58

makeConstraints

-0.56

est

-0.54

arson

-0.54

 steuer

-0.54

 MessageBoxIcon

-0.53

POSITIVE LOGITS

GoogleMap

0.99

goog

0.97

 kaynağından

0.91

 Google

0.89

attere

0.88

goo

0.87

ized

0.84

goo

0.82

 holidays

0.81

hmigung

0.80

Activations Density 0.072%

mentions of Google and its products or services

No Comments

No Known Activations