© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 5674
    Prev
    Next
    INDEX
    Explanations

    references to hills and elevated terrains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Knockout
    -0.81
    ropical
    -0.79
     Breda
    -0.79
    Quo
    -0.78
     gefü
    -0.77
    ellas
    -0.76
    "],
    
    -0.76
    toMatchSnapshot
    -0.75
    loroethene
    -0.73
    emias
    -0.72
    POSITIVE LOGITS
     hill
    1.90
     Hill
    1.88
    Hill
    1.81
     hills
    1.80
     HILL
    1.75
    hill
    1.63
     Hills
    1.62
    Hills
    1.44
    HILL
    1.42
     HILLS
    1.27
    Activations Density 0.063%

    No Known Activations