© 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. 24-GEMMASCOPE-RES-16K
    11. 8950
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of software features and components

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

    tables or grids

    np_acts-logits-general · gemini-2.0-flash

    data tables and grids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ferrer
    -0.40
    addFlags
    -0.39
     isSet
    -0.36
    AlterField
    -0.35
    Documented
    -0.35
    xFFFFFF
    -0.35
     considérons
    -0.34
    PasswordEncoder
    -0.33
    prepareStatement
    -0.33
     aislado
    -0.33
    POSITIVE LOGITS
    TypedDataSet
    0.81
     DataTable
    0.65
     tables
    0.62
    XtraGrid
    0.61
     table
    0.60
     tableView
    0.57
    JTable
    0.56
     spreadsheet
    0.56
     rows
    0.56
    DataTable
    0.54
    Activations Density 0.552%

    No Known Activations