© 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. 18-GEMMASCOPE-RES-16K
    11. 16346
    Prev
    Next
    INDEX
    Explanations

    documents or text related to medical conditions and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Uncommon words or tokens

    np_acts-logits-general · gemini-2.0-flash

    health outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.87
     to
    -0.77
     a
    -0.72
     is
    -0.71
    anhänger
    -0.70
    bedarf
    -0.69
    .
    -0.67
     two
    -0.67
    ,
    -0.66
    ensuche
    -0.65
    POSITIVE LOGITS
     Roskov
    1.08
    UnusedPrivate
    1.00
     doubtnut
    0.99
     فريبيس
    0.93
     ſche
    0.92
    webElementXpaths
    0.91
    WithIOException
    0.90
    ſelf
    0.88
     Jefus
    0.88
     NSM
    0.88
    Activations Density 0.053%

    No Known Activations