© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7072
    Prev
    Next
    INDEX
    Explanations

    sections that indicate the beginning or end of a document or segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vierno
    -0.55
    IVEREF
    -0.53
    Читати
    -0.52
     aiz
    -0.51
    ScopeManager
    -0.51
     textStatus
    -0.50
    FTFY
    -0.47
    outchouc
    -0.47
     desember
    -0.47
    ypeł
    -0.47
    POSITIVE LOGITS
    ंदीखरीदारी
    0.60
    GraphicsUnit
    0.59
     propOrder
    0.56
     initComponents
    0.55
    }=(\
    0.54
     ResourceManager
    0.53
    forName
    0.52
     drag
    0.51
     désolés
    0.50
     InputDecoration
    0.50
    Activations Density 0.077%

    No Known Activations