© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3219
    Prev
    Next
    INDEX
    Explanations

    specific terms and parameters related to software functions and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Su" or "SU"

    np_acts-logits-general · gemini-2.0-flash

    words starting with SU

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamen
    -0.60
    writeFieldEnd
    -0.53
    Peb
    -0.53
    WEBPACK
    -0.52
    TestingModule
    -0.52
    olk
    -0.52
     Wikimedijinoj
    -0.51
    jgl
    -0.51
     Zem
    -0.51
    RTEX
    -0.51
    POSITIVE LOGITS
     SU
    2.14
     Su
    2.10
    Su
    2.07
     su
    1.90
    SU
    1.87
     Sutherland
    1.75
     Suzy
    1.70
     Suarez
    1.69
    su
    1.68
    Sus
    1.67
    Activations Density 0.351%

    No Known Activations