© 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. 22-GEMMASCOPE-RES-16K
    6. 2661
    Prev
    Next
    INDEX
    Explanations

    commentary or annotations in code

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

    Code comments or headers

    np_acts-logits-general · gemini-2.0-flash

    // and TODO comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pratique
    -0.74
    )");
    
    -0.73
    '));
    
    -0.72
    dataclass
    -0.69
    المكان
    -0.68
    getSeconds
    -0.67
    heits
    -0.65
    :");
    
    -0.64
    Contactez
    -0.64
    MergeFrom
    -0.63
    POSITIVE LOGITS
     TODO
    1.00
     //
    0.91
    TODO
    0.88
    /////
    0.84
    //
    0.83
    ////
    0.77
    //
    0.77
    ="//
    0.72
    );//
    0.70
    //////
    0.69
    Activations Density 0.059%

    No Known Activations