© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 12870
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values and specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.60
    CloseOperation
    -0.52
    ThroughAttribute
    -0.50
     defaultstate
    -0.48
    webElementXpaths
    -0.47
    تقاوى
    -0.47
     насељу
    -0.46
    WebServlet
    -0.45
     ویکی‌پدیای
    -0.45
    TypedDataSet
    -0.45
    POSITIVE LOGITS
    ieteur
    0.44
    displayquote
    0.42
     Chwiliwch
    0.42
    ']);
    
    0.41
    '));
    
    0.41
    "]);
    
    0.41
    |()
    0.40
    ()];
    0.40
    FieldBuilder
    0.40
    ()]);
    0.39
    Activations Density 0.860%

    No Known Activations