© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14728
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, processes, and their impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".
    
    -0.77
    "),
    
    -0.73
    '),
    
    -0.64
    ?";
    -0.62
    )");
    
    -0.61
    \\
    
    -0.61
    ="";
    
    -0.61
    ?",
    -0.60
    ?',
    -0.60
    "){
    
    -0.59
    POSITIVE LOGITS
    <bos>
    0.73
     térm
    0.71
    存于互联网档案馆
    0.69
     LCCN
    0.67
    ADELPHIA
    0.64
    Spoljašnje
    0.63
     chré
    0.63
    labus
    0.63
     espagnole
    0.62
     مشارکت‌کنندگان
    0.61
    Activations Density 8.096%

    No Known Activations