INDEX

Explanations

terms related to data representation and database information

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

German, Spanish, or Japanese text

np_acts-logits-general · gemini-2.0-flash

reflexive pronouns

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

WriteTagHelper

-0.62

 Италијани

-0.50

 Kunt

-0.49

intios

-0.49

[*]

-0.49

+')

-0.46

hung

-0.46

thunk

-0.45

 useStyles

-0.45

‍♂️

-0.44

POSITIVE LOGITS

 sich

1.49

 się

1.38

 zich

1.19

 themselves

1.02

 himself

0.99

 herself

0.96

 itself

0.94

 yourself

0.93

 oneself

0.92

 yourselves

0.92

Activations Density 0.041%

terms related to data representation and database information

German, Spanish, or Japanese text

reflexive pronouns

No Comments

No Known Activations