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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 15228
    Prev
    Next
    INDEX
    Explanations

    references to girls and boys, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.69
    )");
    
    -0.64
    "';
    -0.61
     navideñas
    -0.61
    >");
    
    -0.60
     cenar
    -0.60
    cipe
    -0.59
    BeginInit
    -0.58
    "]').
    -0.58
    )}_
    -0.56
    POSITIVE LOGITS
     girl
    3.56
     girls
    3.19
     Girl
    3.15
    girl
    3.06
     GIRL
    3.02
    Girl
    2.98
     Girls
    2.92
    girls
    2.82
    Girls
    2.78
     GIRLS
    2.77
    Activations Density 0.036%

    No Known Activations