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. 5-GEMMASCOPE-RES-16K
    6. 10213
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in a dataset context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '));
    
    -0.99
    `,
    
    -0.86
    "));
    
    -0.84
    )");
    
    -0.83
     StatefulWidget
    -0.78
    .";
    
    -0.76
    ']);
    
    -0.76
    )];
    
    -0.75
    EndInit
    -0.74
     initComponents
    -0.73
    POSITIVE LOGITS
    //
    2.04
    //
    1.75
     //
    1.74
    ,//
    1.45
    ="//
    1.43
    ("//
    1.42
    );//
    1.38
     "//
    1.37
    )//
    1.37
    ;//
    1.35
    Activations Density 0.071%

    No Known Activations