© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 7133
    Prev
    Next
    INDEX
    Explanations

    instances of specific terms that signal the beginning of a significant statement or concept

    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
     sauvages
    -0.75
     normaux
    -0.72
     réfugi
    -0.72
     nationaux
    -0.69
     réglable
    -0.69
     grecque
    -0.67
     gratuits
    -0.67
     suivants
    -0.66
     spéciaux
    -0.66
     whoſe
    -0.65
    POSITIVE LOGITS
    <bos>
    0.99
    __':
    0.82
     ExecuteAsync
    0.77
    tanleria
    0.74
    IntoConstraints
    0.73
    makeConstraints
    0.68
    __":
    0.67
    '};
    0.65
    OwnProperty
    0.65
    tagHelperRunner
    0.60
    Activations Density 0.656%

    No Known Activations