Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61070
    Prev
    Next
    INDEX
    Explanations

    references to research organizations and their commitments to medical advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mergeFrom
    -0.87
    FieldBuilder
    -0.81
    CPtr
    -0.75
    ConstraintMaker
    -0.75
     unknownFields
    -0.69
    ThroughAttribute
    -0.68
    migrationBuilder
    -0.67
     initComponents
    -0.66
    NameInMap
    -0.66
    出版年
    -0.64
    POSITIVE LOGITS
    setof
    0.65
     recevrez
    0.60
    testens
    0.57
    ChildIndex
    0.57
    kään
    0.57
     douceur
    0.56
    textAppearance
    0.56
     esfuer
    0.55
     بتاريخ
    0.55
     quieran
    0.55
    Activations Density 0.195%

    No Known Activations