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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14195
    Prev
    Next
    INDEX
    Explanations

    phrases involving "set of" followed by a number or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.89
     poffible
    -0.85
     itſelf
    -0.81
     perfons
    -0.77
    তথ্যসূত্র
    -0.76
     Majefty
    -0.75
     laſt
    -0.74
     houſe
    -0.74
     uptime
    -0.72
     ſtate
    -0.71
    POSITIVE LOGITS
     set
    0.89
     sets
    0.88
    ]){
    
    0.85
    )=>{
    
    0.80
     Sets
    0.78
    セット
    0.77
     Set
    0.76
    %"),
    0.74
     aset
    0.74
    ']);
    
    0.73
    Activations Density 0.030%

    No Known Activations