© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 10554
    Prev
    Next
    INDEX
    Explanations

    sentences that clearly state or define something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SceneManagement
    -0.68
    ingly
    -0.65
    ViewImports
    -0.61
    AndEndTag
    -0.60
    الدراسه
    -0.57
     uſed
    -0.57
    évaluateur
    -0.56
     Seul
    -0.54
     utafitiHapana
    -0.54
    LSTM
    -0.52
    POSITIVE LOGITS
     the
    1.01
    在于
    0.77
     that
    0.72
     probably
    0.70
     a
    0.70
     those
    0.69
     twofold
    0.68
     an
    0.68
     their
    0.65
    namely
    0.64
    Activations Density 0.230%

    No Known Activations