© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7435
    Prev
    Next
    INDEX
    Explanations

    the concept of factors influencing various outcomes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.54
    inghouse
    -0.47
     CanadaChoose
    -0.47
     siang
    -0.47
     McKee
    -0.45
     Entrega
    -0.44
     Heim
    -0.44
     uș
    -0.43
    escrit
    -0.43
    udesta
    -0.43
    POSITIVE LOGITS
     factor
    1.91
     Factor
    1.83
     factors
    1.77
    factor
    1.74
    Factor
    1.73
     FACTOR
    1.66
     Factors
    1.63
    Factors
    1.55
    factors
    1.52
    FACTOR
    1.51
    Activations Density 0.198%

    No Known Activations