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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-GEMMASCOPE-RES-16K
    6. 1900
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delaire
    -0.84
    ]";
    -0.82
     StatelessWidget
    -0.81
    openzeppelin
    -0.79
    `;
    
    -0.78
    .";
    
    -0.78
     Efq
    -0.78
     "");
    
    -0.77
    */;
    -0.76
    []
    
    -0.75
    POSITIVE LOGITS
    And
    1.25
     And
    1.14
    AND
    0.70
    Và
    0.70
    もちろん
    0.66
     AND
    0.66
    何より
    0.64
     Andi
    0.63
     importantly
    0.62
    люс
    0.60
    Activations Density 0.076%

    No Known Activations