© 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. 36-GEMMASCOPE-RES-16K
    11. 14665
    Prev
    Next
    INDEX
    Explanations

    the declaration of methods in a programming code

    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
     onOptions
    -0.35
    StandardCharsets
    -0.34
    ‌پدی
    -0.34
     getItemCount
    -0.33
     isSet
    -0.28
    ánto
    -0.27
     произо
    -0.27
     jspb
    -0.27
     Connectez
    -0.26
     odc
    -0.26
    POSITIVE LOGITS
     contextLoads
    0.74
     void
    0.69
     VOID
    0.65
     Awake
    0.65
     للمعارف
    0.64
    WaitGroup
    0.63
    الحياه
    0.62
    __":
    0.62
     Void
    0.61
    awakeFromNib
    0.60
    Activations Density 0.042%

    No Known Activations