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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15402
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical values and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.80
    hassee
    -0.69
    رشف
    -0.68
     CascadeType
    -0.66
     Stoner
    -0.66
     ویکی‌پدیای
    -0.65
    fjspx
    -0.65
    myModal
    -0.64
    niad
    -0.62
    EClass
    -0.62
    POSITIVE LOGITS
    )");
    0.57
    ++){
    0.55
    bindParam
    0.53
    ")){
    0.53
    ++){
    0.52
    <tbody>
    0.52
    >--}}
    0.51
     تضيفلها
    0.51
    "])){
    0.51
    mrow
    0.51
    Activations Density 0.399%

    No Known Activations