© 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. 4-GEMMASCOPE-RES-16K
    11. 10546
    Prev
    Next
    INDEX
    Explanations

    references to services and features offered by an app or business

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réessayer
    -0.62
    Viited
    -0.49
    )}_
    -0.46
    diye
    -0.46
     mahdollis
    -0.46
    gree
    -0.45
     witness
    -0.45
     Witness
    -0.45
    diyah
    -0.44
    insky
    -0.44
    POSITIVE LOGITS
     GenerationType
    0.75
     propOrder
    0.73
    出版年
    0.72
    #+#
    0.70
    WaitGroup
    0.70
    Demografia
    0.69
     initComponents
    0.69
    esModule
    0.68
    
    0.68
    ContentLoaded
    0.67
    Activations Density 0.402%

    No Known Activations