© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7990
    Prev
    Next
    INDEX
    Explanations

    specific naming conventions and acronyms related to databases and research methodologies

    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
    DoubleQuotes
    -0.83
    mobileqq
    -0.81
     дописавши
    -0.80
    WebVitals
    -0.76
    ValueStyle
    -0.74
     متعلقه
    -0.74
    makeConstraints
    -0.71
     مرئيه
    -0.71
     saites
    -0.70
    writeFieldEnd
    -0.69
    POSITIVE LOGITS
     planas
    0.66
     vertes
    0.65
     sauvages
    0.61
    S
    0.61
     africains
    0.61
     électriques
    0.60
    same
    0.60
     poussière
    0.57
    lijck
    0.56
     pâtes
    0.56
    Activations Density 0.623%

    No Known Activations