© 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. 10-GEMMASCOPE-RES-16K
    6. 4200
    Prev
    Next
    INDEX
    Explanations

    references to file types and specific file formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CopyWith
    -0.76
    ніципалі
    -0.73
    /#{
    -0.70
    kloped
    -0.69
     jsPsych
    -0.69
     &___
    -0.68
    Spoljašnje
    -0.63
    QtWidgets
    -0.62
     StringTokenizer
    -0.62
     sade
    -0.60
    POSITIVE LOGITS
     مشين
    0.69
     Wayback
    0.59
     صوتيه
    0.56
     дописавши
    0.53
     rowspan
    0.52
    期刊论文
    0.50
    <eos>
    0.49
    الصفحه
    0.49
    |}
    0.47
    DockStyle
    0.45
    Activations Density 0.121%

    No Known Activations