© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 22863
    Prev
    Next
    INDEX
    Explanations

    the presence of beginning markers or indicators in various contexts

    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
    ('/:
    -0.50
    UNGE
    -0.49
     Sta
    -0.49
     báo
    -0.47
    ölf
    -0.47
     der
    -0.46
    มาย
    -0.46
    cookieParser
    -0.46
     sta
    -0.46
     San
    -0.46
    POSITIVE LOGITS
    styleType
    0.96
    ArrowToggle
    0.94
     ་་
    0.82
     Roskov
    0.80
    apimachinery
    0.79
    ReusableCell
    0.78
     оригіналу
    0.77
    ьаж
    0.76
    PMailer
    0.75
     iſt
    0.75
    Activations Density 0.305%

    No Known Activations