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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6143
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to user interface (UI) components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    customizable chatbox overrides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.81
    rungsseite
    -0.80
    invokeLater
    -0.77
    GEBURTSDATUM
    -0.77
    StoryboardSegue
    -0.73
    EDEFAULT
    -0.73
    TargetException
    -0.70
    XmlEnum
    -0.70
     teórico
    -0.68
    RegistryLite
    -0.68
    POSITIVE LOGITS
     customizable
    0.64
     customization
    0.56
     customized
    0.52
     customize
    0.52
     custom
    0.49
     IMO
    0.48
     customizing
    0.47
     sliders
    0.47
    widget
    0.47
     nice
    0.47
    Activations Density 0.248%

    No Known Activations