© 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. 29909
    Prev
    Next
    INDEX
    Explanations

    markers indicating the beginning of a new section or block of text

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

    plays dates and numbers

    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
    GEBURTSDATUM
    -1.20
    Архівовано
    -0.88
    HasForeignKey
    -0.81
    setViewportView
    -0.81
    ChildScrollView
    -0.81
    verwijspagina
    -0.77
    });*/
    -0.77
    曖昧さ回避
    -0.76
    مراجع
    -0.75
    isSuccessful
    -0.75
    POSITIVE LOGITS
    <h2>
    0.86
    ↵↵
    0.79
    <h3>
    0.69
    <eos>
    0.68
    <blockquote>
    0.63
     cât
    0.61
    <b>
    0.60
     vectorielles
    0.57
     homoto
    0.56
    [toxicity=0]
    0.56
    Activations Density 0.002%

    No Known Activations