Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    inline functions and references to laptops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.05
     protoimpl
    -0.74
    )))));
    -0.72
    ViewFeatures
    -0.70
    '",
    -0.69
    )";
    -0.68
    )".
    -0.68
    iyle
    -0.68
     XNUMX
    -0.66
    )";
    
    -0.65
    POSITIVE LOGITS
    $}
    0.67
    ActionCreators
    0.61
     חיצוניים
    0.58
    fully
    0.58
     مشين
    0.57
    sidemargin
    0.55
     StatelessWidget
    0.53
     demain
    0.53
    SpringRunner
    0.52
    onPressed
    0.51
    Activations Density 0.124%

    No Known Activations