© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16120
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to engineering or scientific processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lapar
    -0.48
     Nicosia
    -0.48
     bearing
    -0.47
     Laredo
    -0.47
    .
    -0.47
    ลำ
    -0.46
    Malo
    -0.46
     Carroll
    -0.45
     gree
    -0.45
    Pron
    -0.45
    POSITIVE LOGITS
    />";
    1.06
     تضيفلها
    1.02
    )";
    
    1.00
     Audiodateien
    0.98
    )");
    
    0.97
     mergeFrom
    0.88
    '>
    
    0.87
     SafeMath
    0.86
     ),
    
    0.85
    ]();
    0.83
    Activations Density 0.692%

    No Known Activations