© 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. 21-GEMMASCOPE-RES-16K
    11. 9405
    Prev
    Next
    INDEX
    Explanations

    phrases related to turning points or significant moments in a discussion or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.71
    __(/*!
    -0.60
     disponibilités
    -0.57
     كومونز
    -0.56
     Италијани
    -0.56
    最快更新
    -0.55
     ***!
    -0.53
    MLLoader
    -0.52
    uellement
    -0.52
     linkovi
    -0.50
    POSITIVE LOGITS
     point
    4.03
    point
    3.57
     points
    3.36
     Point
    3.33
    Point
    3.27
     POINT
    3.26
    points
    3.07
    POINT
    3.05
     Points
    2.94
    Points
    2.69
    Activations Density 0.428%

    No Known Activations