© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 103
    Prev
    Next
    INDEX
    Explanations

    content related to website functionality and user experience optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.82
    RenderAtEndOf
    -0.78
    InvalidProtocol
    -0.77
     NSCoder
    -0.71
    IntoConstraints
    -0.70
    HideFlags
    -0.69
     utafitiHapana
    -0.69
    makeConstraints
    -0.69
    +#+
    -0.67
    Vidite
    -0.67
    POSITIVE LOGITS
     guests
    1.03
     customers
    0.97
     clients
    0.84
     Guests
    0.82
     Customers
    0.79
    guests
    0.78
     customer
    0.77
    Guests
    0.76
     users
    0.76
    Customers
    0.75
    Activations Density 0.386%

    No Known Activations