© 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. 8609
    Prev
    Next
    INDEX
    Explanations

    specific identifiers, references, or categories in text

    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
    ⓧ
    -0.64
    <h1>
    -0.63
    package
    -0.63
    import
    -0.57
    //
    -0.56
    #
    -0.56
    #!/
    -0.54
    <?
    -0.50
    źródło
    -0.49
    Czytaj
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.72
    <bos>
    0.72
    存于互联网档案馆
    0.69
    IsContent
    0.67
     ब्रेकडाउन
    0.66
    HtmlAttribute
    0.65
    AndEndTag
    0.64
    archiviato
    0.63
     ویکی‌آمباردا
    0.63
     bezeichneter
    0.62
    Activations Density 4.425%

    No Known Activations