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. 3-GEMMASCOPE-RES-16K
    6. 8472
    Prev
    Next
    INDEX
    Explanations

    structured data such as code or configuration text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     own
    -0.63
    Skocz
    -0.60
     Sergi
    -0.56
    boa
    -0.54
    '
    -0.54
    DispatchToProps
    -0.52
    ixas
    -0.49
    ピース
    -0.49
     (
    -0.49
    )
    -0.49
    POSITIVE LOGITS
    Personendaten
    1.10
     kaarangay
    0.88
    elemField
    0.87
    GEBURTSDATUM
    0.84
     ویکی‌پدی
    0.83
     AspNetCore
    0.79
     Wikimedijinoj
    0.78
    EDEFAULT
    0.75
    astéro
    0.72
    فایل‌لار
    0.71
    Activations Density 0.259%

    No Known Activations