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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10924
    Prev
    Next
    INDEX
    Explanations

    references to widgets or GUI components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.82
    最快更新
    -0.73
     /\.(
    -0.70
     imageNamed
    -0.68
     InputDecoration
    -0.68
    /*
    -0.68
     SqlConnection
    -0.66
    SuppressMessage
    -0.66
     AllAfrica
    -0.66
    /**
    -0.65
    POSITIVE LOGITS
    Widget
    2.04
     Widget
    2.01
     widget
    1.96
     createState
    1.93
     widgets
    1.86
     Widgets
    1.85
    widget
    1.69
    widgets
    1.55
    WIDGET
    1.50
    Widgets
    1.48
    Activations Density 0.070%

    No Known Activations