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. 6704
    Prev
    Next
    INDEX
    Explanations

    references to 'guys' and related terms, indicating a focus on informal group dynamics or relationships

    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
     SafeMath
    -0.87
    "]);
    
    -0.85
    "])
    
    -0.83
    "];
    
    -0.82
    $")
    -0.81
    )");
    
    -0.80
    }]{
    -0.79
    ']")
    -0.79
    "):
    
    -0.78
     ExecuteAsync
    -0.76
    POSITIVE LOGITS
     guys
    1.03
     boys
    0.99
     girl
    0.93
     boy
    0.89
     guy
    0.89
     girls
    0.87
     lads
    0.78
     GUYS
    0.74
    guys
    0.72
    Guys
    0.70
    Activations Density 0.118%

    No Known Activations