© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14985
    Prev
    Next
    INDEX
    Explanations

    sections or elements in documents, particularly markings like brackets and asterisks signaling emphasis or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.80
    ↵↵↵
    -0.79
    webElementXpaths
    -0.73
    /
    -0.69
    ,
    -0.68
    SharedDtor
    -0.66
     […]
    -0.62
     to
    -0.62
     
    -0.62
     in
    -0.62
    POSITIVE LOGITS
    ?}
    0.92
    .}
    0.83
     -}
    0.81
    !}
    0.77
     :}
    0.76
     conseguenze
    0.73
     ""}
    0.72
     chrétiens
    0.72
     colorés
    0.71
     niedersachsen
    0.69
    Activations Density 0.017%

    No Known Activations