© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    words indicating positive or negative quality assessments

    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
     mogelijkheden
    -0.77
     Ausführungen
    -0.73
     dilutions
    -0.71
     timings
    -0.69
     perturbations
    -0.68
     betweenstory
    -0.68
     voordelen
    -0.67
     Auswirkungen
    -0.67
     axioms
    -0.67
     signatures
    -0.66
    POSITIVE LOGITS
     relationship
    0.69
     enfans
    0.68
     pair
    0.65
     version
    0.63
     degree
    0.62
     prêtres
    0.61
     combination
    0.61
     handful
    0.60
     series
    0.60
     amount
    0.60
    Activations Density 0.939%

    No Known Activations