© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-GEMMASCOPE-RES-16K
    11. 15400
    Prev
    Next
    INDEX
    Explanations

    references to fenugreek and its nutritional or health-related properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kerajaan
    -0.71
     Infór
    -0.68
     Keuangan
    -0.63
     Lingkungan
    -0.63
    ronpa
    -0.62
    umumkan
    -0.60
     navideña
    -0.60
     Gubernur
    -0.58
     Besar
    -0.57
    คืน
    -0.56
    POSITIVE LOGITS
    ::_('
    0.49
     UIAlert
    0.46
     golf
    0.45
    issory
    0.44
    jfree
    0.44
     soft
    0.43
     Lazy
    0.39
     french
    0.39
     cr
    0.38
    builtins
    0.38
    Activations Density 2.473%

    No Known Activations