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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14189
    Prev
    Next
    INDEX
    Explanations

    import statements and class definitions within code

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

    Start of C++ or C# code, with "using" or "import"

    np_acts-logits-general · gemini-2.0-flash

    proposed estimators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -1.06
    messageInfo
    -0.82
    featureID
    -0.75
    
    -0.71
    ſelben
    -0.71
    IntoConstraints
    -0.71
     protoimpl
    -0.70
     محفوظة
    -0.70
     препратки
    -0.69
     geſch
    -0.67
    POSITIVE LOGITS
    import
    0.79
     import
    0.60
     importar
    0.41
    以及
    0.37
     importa
    0.35
     importing
    0.33
    ↵↵↵
    0.32
    using
    0.31
     serta
    0.30
     require
    0.29
    Activations Density 0.088%

    No Known Activations