© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30463
    Prev
    Next
    INDEX
    Explanations

    elements related to data handling and analysis within a computing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thanks in other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __;
    -0.85
    zzleHttp
    -0.75
    adaptiveStyles
    -0.75
     EClass
    -0.75
    writeFieldEnd
    -0.69
    twimg
    -0.68
    ScopeManager
    -0.65
    
    -0.65
    principalColumn
    -0.64
    MENAFN
    -0.64
    POSITIVE LOGITS
    ďaka
    0.90
     dzięki
    0.83
     grazie
    0.80
    也不用
    0.74
     gracias
    0.73
     grâce
    0.71
     thanks
    0.69
    也能
    0.69
    grazie
    0.69
    Dzięki
    0.64
    Activations Density 0.340%

    No Known Activations