© 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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5329
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures, particularly those associated with object manipulation and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.66
    ;';
    -0.50
     Photocase
    -0.50
    loroethene
    -0.49
    GenerationType
    -0.49
     defaultstate
    -0.48
    出版年
    -0.46
    aarrggbb
    -0.46
     }}$}
    -0.46
     ""))
    -0.45
    POSITIVE LOGITS
    ");
    
    0.60
    "];
    
    0.57
     ''
    0.57
    );
    
    0.56
    ');
    
    0.54
    ());
    
    0.50
    >();
    
    0.49
    ];
    
    0.47
    '];
    
    0.47
     "");
    
    0.45
    Activations Density 0.190%

    No Known Activations