© 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. 6412
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations, particularly derivatives and equations

    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
    balleur
    -0.78
    rawDesc
    -0.75
    ScopeManager
    -0.69
    httphttps
    -0.68
    ValueStyle
    -0.66
    RTHOOK
    -0.66
    ConstraintMaker
    -0.65
    WireFormatLite
    -0.63
     mergeFrom
    -0.63
    CppMethod
    -0.62
    POSITIVE LOGITS
    sin
    0.35
    x
    0.34
    √
    0.32
    sqrt
    0.31
     x
    0.29
    log
    0.29
    ln
    0.28
     sin
    0.27
    Leg
    0.27
     CGA
    0.27
    Activations Density 4.313%

    No Known Activations