© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 16953
    Prev
    Next
    INDEX
    Explanations

    terms related to "auto" or "automatic" processes and concepts, particularly in medical or biological contexts

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

    autocrine, autologous, autosomal, autoclave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FunctionFlags
    -0.36
    BagLayout
    -0.36
    expliquer
    -0.35
     pleaſure
    -0.35
     aikaa
    -0.34
     enää
    -0.34
     počas
    -0.34
     hiperten
    -0.34
    mäß
    -0.33
    habitude
    -0.33
    POSITIVE LOGITS
     auto
    0.92
     Auto
    0.89
    Auto
    0.88
    auto
    0.87
     AUTO
    0.81
     EconPapers
    0.79
    AUTO
    0.72
     autos
    0.66
     Autos
    0.65
     aut
    0.64
    Activations Density 0.016%

    No Known Activations