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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11613
    Prev
    Next
    INDEX
    Explanations

    terms related to particle methods and their applications in filtering and estimation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.68
    fjspx
    -0.63
     مشين
    -0.58
    ScopeManager
    -0.54
    AccessorTable
    -0.52
    webElementXpaths
    -0.50
    ISupport
    -0.50
    TestingModule
    -0.49
     للمعارف
    -0.49
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
     Clusters
    0.43
     clusters
    0.42
    clusters
    0.42
     Packet
    0.41
     Bead
    0.40
     Cluster
    0.39
    ünstler
    0.39
     Loaf
    0.39
    Cluster
    0.38
     MMC
    0.38
    Activations Density 0.545%

    No Known Activations