© 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. 4786
    Prev
    Next
    INDEX
    Explanations

    technical terms and proteins related to scientific research, particularly in the field of biology and cell signaling

    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
    multer
    -0.56
    secret
    -0.51
    Bakgrunnsstoff
    -0.51
    UserScript
    -0.47
     DROP
    -0.47
     Mackey
    -0.47
     secret
    -0.46
    dição
    -0.46
     Salford
    -0.46
     Nel
    -0.46
    POSITIVE LOGITS
    Geplaatst
    0.94
     kinase
    0.73
     незавершена
    0.66
     phosphorylation
    0.65
     kinases
    0.65
     الاطلاع
    0.62
    MessageOf
    0.60
     phosphatase
    0.60
     Phosph
    0.56
    UnsafeEnabled
    0.56
    Activations Density 1.409%

    No Known Activations