© 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. 35-GEMMASCOPE-RES-16K
    11. 5479
    Prev
    Next
    INDEX
    Explanations

    medical and genetic terminology related to patient conditions and mutations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.49
    Promotion
    -0.43
    tênis
    -0.43
    исленность
    -0.43
    HtmlAttribute
    -0.43
     uLocal
    -0.43
     فريبيس
    -0.41
     DbSet
    -0.41
     newBuilder
    -0.41
    TemporalType
    -0.41
    POSITIVE LOGITS
     autos
    0.69
     congenital
    0.60
     Autos
    0.60
     inherited
    0.59
    autos
    0.58
    Autos
    0.57
     defects
    0.54
    先天
    0.52
     affected
    0.51
     hereditary
    0.50
    Activations Density 1.274%

    No Known Activations