© 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. 0-GEMMASCOPE-RES-16K
    11. 11415
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to performance metrics

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    expandindo
    -0.99
    #
    -0.92
    extAlignment
    -0.90
     EconPapers
    -0.85
    ngdoc
    -0.80
    Xna
    -0.80
    GOTREF
    -0.78
     estekak
    -0.76
     itſelf
    -0.76
    /**
    -0.75
    POSITIVE LOGITS
     performance
    1.06
    performance
    0.95
    perform
    0.91
     Performance
    0.90
    Performance
    0.88
     =>
    0.88
     PERFORMANCE
    0.79
     performances
    0.79
    =>
    0.77
     Thunder
    0.72
    Activations Density 0.116%

    No Known Activations