© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1401
    Prev
    Next
    INDEX
    Explanations

    legal terminologies related to discrimination and workplace regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.40
    withOpacity
    -0.36
     الاطلاع
    -0.36
     berlangsung
    -0.36
     desvan
    -0.33
    mientos
    -0.33
    LikeLike
    -0.33
    UnusedPrivate
    -0.33
    jemahan
    -0.32
    ковник
    -0.32
    POSITIVE LOGITS
    __":
    0.56
    "+
    
    0.55
     مرئيه
    0.55
     ویکی‌پدی
    0.54
    SequentialGroup
    0.53
    astify
    0.52
    :✨
    0.50
     Roskov
    0.50
    MessageOf
    0.50
    __":
    
    0.49
    Activations Density 1.539%

    No Known Activations