© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6574
    Prev
    Next
    INDEX
    Explanations

    references to indexed or structured data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <blockquote>
    -0.38
    webElementXpaths
    -0.32
     propOrder
    -0.32
    كويكب
    -0.30
    :✨
    -0.29
    getSystemService
    -0.27
    Comté
    -0.27
     untreated
    -0.27
     TextInputType
    -0.27
     насељу
    -0.26
    POSITIVE LOGITS
    ())
    
    0.79
    。)
    0.74
    。
    
    0.73
    ()))
    
    0.71
    "]);
    
    0.70
    ());
    
    0.70
    ()){
    
    0.69
    ()}}
    0.69
    ();}
    0.69
    })
    
    0.69
    Activations Density 0.358%

    No Known Activations