© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8123
    Prev
    Next
    INDEX
    Explanations

    references to hotels and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.61
    請繼續往下閱讀
    -0.59
     bacio
    -0.57
    protoimpl
    -0.54
     Taktlose
    -0.54
     TextAppearance
    -0.52
    ロウィン
    -0.50
    localctx
    -0.50
    PhysRev
    -0.47
    errHandler
    -0.47
    POSITIVE LOGITS
     universities
    0.73
     Universities
    0.69
     hotel
    0.61
     College
    0.59
    大学
    0.59
    vars
    0.59
     university
    0.58
     Colleges
    0.57
     college
    0.57
     colleges
    0.57
    Activations Density 0.223%

    No Known Activations