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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 7534
    Prev
    Next
    INDEX
    Explanations

    terms associated with national and competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁿
    -0.55
    >`;
    -0.53
     smart
    -0.52
    <>();
    -0.50
    WillAppear
    -0.50
     @"/
    -0.49
     }},
    -0.49
     artísticas
    -0.48
     sk
    -0.48
    ်း
    -0.48
    POSITIVE LOGITS
     Majefty
    0.88
    DotNetBar
    0.78
     itſelf
    0.76
     myſelf
    0.75
    ArrowToggle
    0.75
     Theſe
    0.71
     Anſ
    0.70
     perſon
    0.69
     متعلقه
    0.69
     ویکی‌پدیا
    0.69
    Activations Density 0.051%

    No Known Activations