© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9354
    Prev
    Next
    INDEX
    Explanations

    the term "tic" in a medical context, particularly relating to psychological or neurological conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    portlet
    -0.56
    lego
    -0.55
    нар
    -0.52
    Stiftung
    -0.49
     trumpets
    -0.47
    ism
    -0.44
     violets
    -0.44
     AppBundle
    -0.44
    ing
    -0.44
    Composable
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.91
     дописавши
    0.83
    ."));
    0.82
    tvguidetime
    0.80
     متعلقه
    0.79
     '*')
    0.78
    makeConstraints
    0.76
    )");
    
    0.75
    %");
    0.75
     Himo
    0.75
    Activations Density 0.036%

    No Known Activations