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. 7406
    Prev
    Next
    INDEX
    Explanations

    terms related to programming, specifically within the context of modules and plugins

    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
    yntaxException
    -0.79
    TagMode
    -0.78
    +#+#
    -0.77
    sizeCache
    -0.77
    TargetException
    -0.74
    WriteBarrier
    -0.74
    BufferException
    -0.72
    makeConstraints
    -0.71
    Javadoc
    -0.71
     SafeMath
    -0.71
    POSITIVE LOGITS
    UserScript
    0.69
    MLLoader
    0.61
     initComponents
    0.56
    AddComponent
    0.55
     муніципалі
    0.54
    nameof
    0.53
     ͡°
    0.52
    Gegen
    0.50
     namens
    0.49
    <?,
    0.48
    Activations Density 0.586%

    No Known Activations