© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    information about cell adhesion and tissue engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.54
     esternos
    -0.45
    $',
    -0.42
    käse
    -0.41
    —”
    -0.41
    ()">
    -0.40
    enetrable
    -0.40
     formaggio
    -0.40
    ufficio
    -0.40
    点此举报
    -0.40
    POSITIVE LOGITS
     belongs
    0.65
     meanwhile
    0.65
     belonged
    0.64
     which
    0.63
     happened
    0.62
     depends
    0.59
     belong
    0.57
     existed
    0.55
     than
    0.54
     therefore
    0.54
    Activations Density 1.642%

    No Known Activations