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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 16109
    Prev
    Next
    INDEX
    Explanations

    historical references to military engagements and specific military units

    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
     Мексичка
    -0.47
    MigrationBuilder
    -0.43
     Autorisations
    -0.42
     AssemblyCompany
    -0.42
     chalet
    -0.40
    toHaveBeenCalled
    -0.40
     مشين
    -0.38
    cristo
    -0.38
    JvmStatic
    -0.38
    chartInstance
    -0.38
    POSITIVE LOGITS
     destroyers
    0.69
     destroyer
    0.66
     carrier
    0.65
     cruisers
    0.63
     fleet
    0.63
     warships
    0.61
     Destroyer
    0.59
     cruiser
    0.58
     battleship
    0.57
     surface
    0.57
    Activations Density 0.210%

    No Known Activations