© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9758
    Prev
    Next
    INDEX
    Explanations

    terms related to renovation and rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MeasureSpec
    -0.63
    mitten
    -0.49
     Interess
    -0.48
    ItemBackground
    -0.48
    LayoutStyle
    -0.48
    ProgressHUD
    -0.48
    monary
    -0.47
     cloud
    -0.47
     Brenda
    -0.47
     softening
    -0.47
    POSITIVE LOGITS
     renovation
    1.02
     renovate
    0.84
     Callback
    0.84
     renovations
    0.83
     Renovation
    0.82
     renovating
    0.80
     rehabilitation
    0.80
     rehab
    0.80
     rehabilit
    0.79
    Renov
    0.78
    Activations Density 0.029%

    No Known Activations