© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4448
    Prev
    Next
    INDEX
    Explanations

    keywords related to military service and enlistment

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

    Enlistment into the military

    np_acts-logits-general · gemini-2.0-flash

    military enlistment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.50
    FormTagHelper
    -0.49
    "}";
    -0.48
    PageRoute
    -0.48
    tagHelperRunner
    -0.48
     surla
    -0.46
     idéia
    -0.44
    Референце
    -0.43
     تضيفلها
    -0.43
     Direktur
    -0.42
    POSITIVE LOGITS
     Army
    1.27
     army
    1.14
    Army
    1.12
     military
    1.11
    army
    1.04
     Military
    1.02
    military
    1.02
    Military
    1.00
     Navy
    0.97
     soldier
    0.88
    Activations Density 0.224%

    No Known Activations