© 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. 11-GEMMASCOPE-RES-16K
    11. 7390
    Prev
    Next
    INDEX
    Explanations

    quantitative data and metrics related to patient treatment and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yczą
    -0.43
     classificação
    -0.36
    essége
    -0.35
    yaitu
    -0.35
     pouvoit
    -0.34
     kaikk
    -0.34
     tudo
    -0.33
     joka
    -0.33
    >";
    -0.32
    ßerdem
    -0.32
    POSITIVE LOGITS
    featureID
    0.64
    五六
    0.62
    三四
    0.62
    ItemBackground
    0.62
    parsedMessage
    0.61
     Audiodateien
    0.59
    jooq
    0.56
    七八
    0.55
    AnchorTagHelper
    0.52
    UseVisualStyle
    0.52
    Activations Density 0.420%

    No Known Activations