© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15050
    Prev
    Next
    INDEX
    Explanations

    references to Android programming and libraries

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

    Code related to Android, Swift, or Apache

    np_acts-logits-general · gemini-2.0-flash

    software development, code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIdentifier
    -0.56
     réunis
    -0.56
     privées
    -0.51
    fromCharCode
    -0.48
     aimé
    -0.47
     réfugiés
    -0.47
     trasero
    -0.47
     manières
    -0.46
     blessés
    -0.46
     impossível
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.92
    LookAnd
    0.88
     QtWidgets
    0.83
     חיצוניים
    0.79
    MigrationBuilder
    0.77
    Autoritní
    0.77
    )":
    0.73
    GEBURTSDATUM
    0.73
    )':
    0.71
    queryInterface
    0.69
    Activations Density 0.045%

    No Known Activations