© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12228
    Prev
    Next
    INDEX
    Explanations

    interactions and relationships in narratives involving personal connections and underlying motives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tē
    -0.35
     Birk
    -0.31
    duct
    -0.31
     tiroirs
    -0.31
     dinilai
    -0.31
    šnje
    -0.31
     najbolj
    -0.31
    Trama
    -0.31
     批量
    -0.30
     minhas
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.79
    richTextPanel
    0.70
    AntiForgeryToken
    0.70
    encodeWith
    0.69
     estekak
    0.69
    BufferException
    0.68
    GEBURTSDATUM
    0.63
     AssemblyVersion
    0.60
     مرئيه
    0.60
     mergeFrom
    0.59
    Activations Density 0.885%

    No Known Activations