© 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. 37-GEMMASCOPE-RES-16K
    11. 5266
    Prev
    Next
    INDEX
    Explanations

    programming keywords and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.88
    GEBURTSDATUM
    -0.85
    bootstrapcdn
    -0.85
    httphttps
    -0.82
    queryInterface
    -0.77
    NameInMap
    -0.75
     ویکی‌پدی
    -0.71
     يتيمه
    -0.70
    SBATCH
    -0.68
    SequentialGroup
    -0.68
    POSITIVE LOGITS
    internal
    0.93
     internal
    0.80
    bool
    0.69
     bool
    0.67
    #
    0.65
    string
    0.64
    public
    0.64
     internes
    0.63
    ///
    0.62
    private
    0.62
    Activations Density 0.062%

    No Known Activations