© 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. 15-GEMMASCOPE-RES-16K
    11. 1917
    Prev
    Next
    INDEX
    Explanations

    terms related to progress and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.69
    CppMethod
    -0.66
    GEBURTSDATUM
    -0.65
    addCriterion
    -0.62
    帖最后由
    -0.62
    RegressionTest
    -0.57
     gyhoeddwyd
    -0.56
     autorytatywna
    -0.54
    DIPSETTING
    -0.52
    ChildScrollView
    -0.49
    POSITIVE LOGITS
    Referències
    0.36
     riz
    0.32
    раздо
    0.32
    ียน
    0.32
     بأن
    0.31
     basados
    0.31
    Trades
    0.31
    ":[{
    0.31
    gado
    0.31
     night
    0.30
    Activations Density 1.443%

    No Known Activations