© 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. 36-GEMMASCOPE-RES-16K
    11. 13120
    Prev
    Next
    INDEX
    Explanations

    UI components and layout structures in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    memberof
    -0.37
    nicamente
    -0.37
    rawdę
    -0.36
    omentos
    -0.36
    numerusform
    -0.36
     preocupes
    -0.34
     listos
    -0.32
    localObject
    -0.32
    woordig
    -0.32
     liệu
    -0.31
    POSITIVE LOGITS
    MigrationBuilder
    0.62
     className
    0.62
     صوتيه
    0.57
    asteroide
    0.55
    className
    0.54
     key
    0.54
     variant
    0.52
    >{
    0.51
     kaarangay
    0.51
     Roskov
    0.49
    Activations Density 0.114%

    No Known Activations