© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13032
    Prev
    Next
    INDEX
    Explanations

    occurrences of curly braces or brackets in mathematical expressions or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
     disambiguazione
    -0.82
    styleType
    -0.79
     ujednoznacz
    -0.73
    SizeMode
    -0.70
    SharedCtor
    -0.69
     lenker
    -0.68
     MainAxisSize
    -0.68
    Rujuakan
    -0.67
     noDo
    -0.67
    webElementXpaths
    -0.67
    POSITIVE LOGITS
    <i>
    0.68
    <b>
    0.61
    <em>
    0.57
    <strong>
    0.55
    {
    0.55
    <u>
    0.52
    CJK
    0.49
    <code>
    0.49
     “
    0.49
     ‘
    0.49
    Activations Density 0.061%

    No Known Activations