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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 3041
    Prev
    Next
    INDEX
    Explanations

    elements and components related to user interface design in programming

    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
     becauſe
    -1.01
     uſed
    -0.97
     myſelf
    -0.93
    Jîn
    -0.89
     архивлан
    -0.86
     raiſ
    -0.84
     whoſe
    -0.84
     ſeveral
    -0.83
     pleaſure
    -0.83
    Kjelder
    -0.83
    POSITIVE LOGITS
    jLabel
    1.13
    groupBox
    0.65
     jLabel
    0.64
    tabPage
    0.61
    MigrationBuilder
    0.59
    LayoutPanel
    0.59
     č
    0.56
    QLabel
    0.56
    labelControl
    0.55
    jPanel
    0.54
    Activations Density 0.006%

    No Known Activations