Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6859
    Prev
    Next
    INDEX
    Explanations

    function calls and database-related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.97
    ConstraintMaker
    -0.93
    GraphicsUnit
    -0.91
     NSCoder
    -0.88
    uxxxx
    -0.88
    tagHelperRunner
    -0.82
    RegressionTest
    -0.77
     nahilalakip
    -0.77
    WriteTagHelper
    -0.76
    GEBURTSDATUM
    -0.76
    POSITIVE LOGITS
     menge
    0.49
    lasi
    0.45
    listdir
    0.45
    fetchAll
    0.44
     trouvez
    0.44
     esteja
    0.43
     gambe
    0.42
     list
    0.42
     daftar
    0.42
    列表
    0.41
    Activations Density 0.185%

    No Known Activations