© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29351
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to algebraic structures

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

    exponentiation of variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.73
    Viitteet
    -0.66
    itinéraire
    -0.63
    itename
    -0.62
    StoryboardSegue
    -0.61
     OFDb
    -0.59
     ModelExpression
    -0.58
     Schwer
    -0.58
     honors
    -0.57
    مقاله
    -0.56
    POSITIVE LOGITS
    createStatement
    0.55
    lético
    0.47
    NonNull
    0.47
     Paglinawan
    0.46
    photobucket
    0.46
    prepareStatement
    0.45
    তথ্যসূত্র
    0.45
     Może
    0.45
    PrototypeOf
    0.45
    mop
    0.44
    Activations Density 1.663%

    No Known Activations