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. 12391
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the application of techniques or methods

    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
    ISupport
    -0.77
     ostavi
    -0.70
    setViewportView
    -0.68
    itinéraire
    -0.64
     ExecuteAsync
    -0.63
    InsertCommand
    -0.62
    parsedMessage
    -0.61
    ISODE
    -0.59
    :✨
    -0.59
    MENAFN
    -0.57
    POSITIVE LOGITS
    الحياه
    0.73
     to
    0.70
     để
    0.63
     upang
    0.63
     чтобы
    0.59
     כדי
    0.55
     وتسجيلات
    0.49
     htons
    0.48
    }));
    
    0.48
    TimeTo
    0.47
    Activations Density 0.555%

    No Known Activations