© 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. 3-GEMMASCOPE-RES-16K
    6. 7966
    Prev
    Next
    INDEX
    Explanations

    quotation marks and their associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moms
    -0.61
     réve
    -0.60
     conosce
    -0.60
    väg
    -0.59
     nationaux
    -0.58
     flavors
    -0.58
     abstrait
    -0.57
    skid
    -0.57
     counselors
    -0.57
    iseur
    -0.57
    POSITIVE LOGITS
    ';
    2.17
    ';
    
    2.15
    )';
    2.03
    !';
    1.95
    ";
    1.94
    >';
    1.91
    }';
    1.90
    )";
    1.87
    ";
    
    1.87
    .';
    1.86
    Activations Density 0.017%

    No Known Activations