© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 29811
    Prev
    Next
    INDEX
    Explanations

    technical terms related to parameters and configurations in a programming or scripting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    options and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.70
    "]);
    
    -0.63
    )');
    -0.60
    _));
    -0.52
    "));
    
    -0.47
    )");
    -0.46
    )')
    -0.45
    "]);
    -0.45
    <eos>
    -0.44
     principales
    -0.43
    POSITIVE LOGITS
    出版年
    0.88
     متعلقه
    0.87
    
    0.82
     विश्वसनीयता
    0.78
    Diwedd
    0.74
    APOLIS
    0.73
    tvguidetime
    0.71
     EconPapers
    0.69
    WebVitals
    0.68
    foundland
    0.68
    Activations Density 0.347%

    No Known Activations