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. 10-GEMMASCOPE-RES-16K
    6. 11797
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their relationships in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echa
    -0.56
    رب
    -0.55
    ecap
    -0.54
    RunWith
    -0.52
     ECS
    -0.50
    ind
    -0.49
    AndroidJUnit
    -0.49
     fer
    -0.48
    낙
    -0.48
     concepts
    -0.47
    POSITIVE LOGITS
    /**
    0.83
     للاسماء
    0.78
     }}"></
    0.77
    #
    0.68
     smtplib
    0.67
    </caption>
    0.66
    __":
    
    0.65
    )");
    
    0.62
    insatz
    0.62
    帖最后由
    0.62
    Activations Density 0.011%

    No Known Activations