Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 129
    Prev
    Next
    INDEX
    Explanations

    references to parent-child relationships and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Possessive pronouns: her, his, my

    np_acts-logits-general · gemini-2.0-flash

    male relationships or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istrinya
    -0.84
    Ladies
    -0.75
    wife
    -0.74
    ladies
    -0.72
     ivelany
    -0.72
     Wife
    -0.71
     girlfriend
    -0.68
     Ladies
    -0.68
    <![
    -0.67
     womens
    -0.67
    POSITIVE LOGITS
     masculino
    0.79
     suaminya
    0.77
    丈夫
    0.73
     masculinos
    0.72
     masculina
    0.72
     Männer
    0.70
     băr
    0.69
     erkek
    0.69
     chồng
    0.67
     male
    0.66
    Activations Density 3.187%

    No Known Activations