© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4006
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "native," particularly in contexts discussing origins or attributes related to identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.47
    ecki
    -0.47
    UrlResolution
    -0.47
    HasColumn
    -0.43
     postIndex
    -0.42
    XmlType
    -0.41
     Davao
    -0.41
     HOLIDAY
    -0.40
    esai
    -0.40
     pæ
    -0.40
    POSITIVE LOGITS
    native
    0.87
     native
    0.85
    Native
    0.65
     Native
    0.61
    natives
    0.57
     nativa
    0.56
     Cart
    0.55
    Życiorys
    0.52
     indigenous
    0.52
    NATIVE
    0.52
    Activations Density 0.156%

    No Known Activations