© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9824
    Prev
    Next
    INDEX
    Explanations

    references to military personnel and their experiences

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

    military context

    np_acts-logits-general · gemini-2.0-flash

    military personnel and ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.76
     ویکی‌پدیا
    -0.73
    interopRequire
    -0.69
    JpaRepository
    -0.66
    帖最后由
    -0.66
    DeleteBehavior
    -0.66
    [++
    -0.65
     betweenstory
    -0.65
     DataTypes
    -0.64
    webElementXpaths
    -0.60
    POSITIVE LOGITS
     military
    1.49
     Military
    1.45
    Military
    1.32
     Army
    1.30
    military
    1.21
     MILITARY
    1.18
    Army
    1.15
     soldiers
    1.10
     Navy
    1.06
     civilian
    1.04
    Activations Density 0.702%

    No Known Activations