© 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 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. 9349
    Prev
    Next
    INDEX
    Explanations

    references to currency, financial transactions, and security features related to banknotes

    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
    BufferException
    -0.42
    SequentialGroup
    -0.41
    XmlAccessorType
    -0.36
    DockStyle
    -0.35
     przes
    -0.34
     afast
    -0.34
    ładka
    -0.34
    SceneManagement
    -0.34
    MessageOf
    -0.33
     فريبيس
    -0.33
    POSITIVE LOGITS
     coin
    2.22
     coins
    2.22
     Coin
    1.93
     Coins
    1.88
    coin
    1.80
    coins
    1.77
    Coin
    1.75
     currency
    1.75
    Coins
    1.68
     coinage
    1.64
    Activations Density 0.288%

    No Known Activations