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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3601
    Prev
    Next
    INDEX
    Explanations

    references to military operations or aviation commands

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

    Military units or commands

    np_acts-logits-general · gemini-2.0-flash

    Military units and bases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.47
    üttel
    -0.31
     Superhost
    -0.30
    Cyfeiriadau
    -0.29
     Paglinawan
    -0.29
    énario
    -0.28
     alimentaire
    -0.28
     zengin
    -0.27
     conocemos
    -0.27
     prácti
    -0.26
    POSITIVE LOGITS
     Military
    0.69
     Militar
    0.68
     militar
    0.68
     Army
    0.66
    Military
    0.66
     barracks
    0.66
     Barracks
    0.65
    Army
    0.65
     militaire
    0.65
     military
    0.63
    Activations Density 0.227%

    No Known Activations