© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1028
    Prev
    Next
    INDEX
    Explanations

    references to Australia and its geographical, cultural, and political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.66
     Infórmanos
    -0.62
    PMailer
    -0.54
     resourceCulture
    -0.53
    AccessorTable
    -0.52
    routeProvider
    -0.50
     Britain
    -0.49
    ategorias
    -0.48
     NSCoder
    -0.47
    英國
    -0.47
    POSITIVE LOGITS
     citizens
    0.58
     nationals
    0.54
     universities
    0.54
     citizen
    0.52
     citizenship
    0.52
     born
    0.50
     shores
    0.50
     natives
    0.48
    RAINE
    0.47
     taxpayers
    0.47
    Activations Density 0.376%

    No Known Activations