© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    commands or suggestions directed at the reader

    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
    +#+#
    -1.10
    WithIOException
    -0.94
    Xna
    -0.86
     linkovi
    -0.85
     BoxDecoration
    -0.81
    PreInfinity
    -0.80
     EconPapers
    -0.79
    IntoConstraints
    -0.78
     estekak
    -0.77
     незавершена
    -0.76
    POSITIVE LOGITS
     yourself
    1.29
     your
    1.07
     yourselves
    0.92
     Yourself
    0.85
     me
    0.72
     gjerne
    0.69
     them
    0.69
     gärna
    0.69
    yourself
    0.66
     YOURSELF
    0.65
    Activations Density 0.453%

    No Known Activations