© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 177
    Prev
    Next
    INDEX
    Explanations

    mentions of programming-related terms, particularly those related to JavaScript and module management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entyfik
    -0.67
    amaño
    -0.65
    ekš
    -0.64
    DataMember
    -0.64
     ſee
    -0.62
    ertale
    -0.61
    acuzzi
    -0.61
    васто
    -0.61
    yakit
    -0.61
     podjet
    -0.60
    POSITIVE LOGITS
    ViewFeatures
    0.92
     مشين
    0.82
    modules
    0.81
    Clik
    0.78
    новништво
    0.71
     DevExpress
    0.69
    thrift
    0.64
    migrationBuilder
    0.64
    cshtml
    0.64
    SequentialGroup
    0.63
    Activations Density 0.017%

    No Known Activations