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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2273
    Prev
    Next
    INDEX
    Explanations

    phrases related to military enlistment and physical criteria for candidates

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

    military service

    np_acts-logits-general · gemini-2.0-flash

    military service recruitment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.61
    kozások
    -0.60
    webElementXpaths
    -0.59
    interopRequire
    -0.58
    rungsseite
    -0.54
     LUMI
    -0.50
    COUVER
    -0.47
     zucca
    -0.47
     createState
    -0.45
     ویکی‌پدیا
    -0.44
    POSITIVE LOGITS
     soldiers
    1.91
     military
    1.91
     soldier
    1.80
     Army
    1.76
     army
    1.73
     Military
    1.69
     Soldiers
    1.67
    Military
    1.61
    military
    1.60
    Soldiers
    1.59
    Activations Density 0.726%

    No Known Activations