© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10222
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or concepts denoted by "Haven" and terms related to arithmetic calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.79
    AutoScale
    -0.79
    ArrowToggle
    -0.75
     HasFactory
    -0.71
     betweenstory
    -0.71
     désolés
    -0.70
     distanciation
    -0.69
    aarrggbb
    -0.68
    InvalidProtocol
    -0.67
    RenderAtEndOf
    -0.66
    POSITIVE LOGITS
     uneven
    0.68
    Haven
    0.66
     Paine
    0.65
     inconsist
    0.63
    istle
    0.62
     Haven
    0.61
     haven
    0.61
    Haz
    0.61
     Haz
    0.60
    ostok
    0.60
    Activations Density 0.116%

    No Known Activations