© 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. 37-GEMMASCOPE-RES-16K
    11. 5617
    Prev
    Next
    INDEX
    Explanations

    references to physical activity in relation to parental involvement and outcomes in children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.49
     padrão
    -0.42
     patent
    -0.41
     patented
    -0.41
     payment
    -0.41
     passage
    -0.40
     parents
    -0.40
     pattern
    -0.39
     pères
    -0.38
     phải
    -0.38
    POSITIVE LOGITS
     SqlCommand
    0.61
    Попис
    0.51
    terno
    0.48
     demografica
    0.47
    BufferException
    0.47
    zzleHttp
    0.47
    CGRectMake
    0.46
    :✨
    0.45
    GenerationType
    0.45
    ItemBackground
    0.45
    Activations Density 0.474%

    No Known Activations