INDEX

Explanations

references to Google and its associated services

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

"Google" followed by various contexts

np_acts-logits-general · gemini-2.0-flash

Google products and services

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

Tikang

-0.63

❋

-0.59

}$)

-0.59

}*/

-0.56

település

-0.54

 appart

-0.52

Rüyada

-0.50

PropTypes

-0.50

 mezz

-0.50

ConstraintMaker

-0.50

POSITIVE LOGITS

 Chrome

0.86

 Google

0.82

Chrome

0.76

Google

0.74

 GOOGLE

0.74

 chrome

0.69

 google

0.68

 googled

0.68

 Stadia

0.67

GoogleApiClient

0.67

Activations Density 0.072%

references to Google and its associated services

"Google" followed by various contexts

Google products and services

No Comments

No Known Activations