© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    code segments related to data encoding and output in PHP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Handwerk
    -0.38
    RenderAtEndOf
    -0.36
    ={
    
    -0.33
    )";
    
    -0.31
    -
    
    -0.31
     soldadura
    -0.31
    ';
    
    -0.31
    itoria
    -0.31
     Bestandteil
    -0.31
    ";
    
    -0.30
    POSITIVE LOGITS
     ?>
    1.09
    ?>
    1.04
    ?>
    
    0.81
     ?>
    
    0.78
    endphp
    0.73
     ?'
    0.64
    ?»
    0.64
    ?><
    0.62
    ;?>
    0.62
     ?"
    0.61
    Activations Density 0.154%

    No Known Activations