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. 6880
    Prev
    Next
    INDEX
    Explanations

    references to procedures and methods in technical or scientific contexts

    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
     HasFactory
    -0.99
     ")");
    -0.98
     StatefulWidget
    -0.93
     ingrat
    -0.91
    HtmlAttribute
    -0.91
    ]--;
    -0.88
     Sext
    -0.88
    "])
    
    -0.87
    )}</
    -0.86
    sizeCache
    -0.85
    POSITIVE LOGITS
     procedures
    1.71
     procedure
    1.69
     Procedures
    1.47
     Procedure
    1.45
    procedures
    1.33
    procedure
    1.31
    Procedure
    1.28
    Procedures
    1.20
     PROCEDURE
    1.18
     proced
    1.09
    Activations Density 0.067%

    No Known Activations