© 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. 0-GEMMASCOPE-RES-16K
    11. 8201
    Prev
    Next
    INDEX
    Explanations

    references to sheets in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.63
     feroit
    -0.54
     pouvoit
    -0.53
     للاسماء
    -0.49
     perfectamente
    -0.48
    ญิง
    -0.47
     sienta
    -0.45
     auroit
    -0.45
     avoient
    -0.44
     valentín
    -0.44
    POSITIVE LOGITS
     sheet
    0.85
     skin
    0.79
     Sheet
    0.75
    Sheet
    0.68
    sheet
    0.67
     SHEET
    0.66
     skins
    0.64
     Skins
    0.62
    VersionUID
    0.62
     Skin
    0.62
    Activations Density 1.566%

    No Known Activations