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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 7298
    Prev
    Next
    INDEX
    Explanations

    text related to military operations and personnel transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.78
    ArgsConstructor
    -0.66
    eseorang
    -0.61
    insee
    -0.61
     dénon
    -0.60
     nakalista
    -0.60
    SequentialGroup
    -0.60
     judiciales
    -0.60
    存于互联网档案馆
    -0.59
    __':
    
    -0.58
    POSITIVE LOGITS
     civilian
    0.66
     billets
    0.66
     capability
    0.65
     Directorate
    0.64
     mission
    0.62
     DoD
    0.61
     augmente
    0.61
     Navy
    0.60
     Army
    0.58
     Joint
    0.58
    Activations Density 0.473%

    No Known Activations