© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5958
    Prev
    Next
    INDEX
    Explanations

    negations and conditions related to checks or validations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fig
    -0.60
     Fig
    -0.55
     والع
    -0.52
    ↵↵↵
    -0.49
     Halen
    -0.49
    ’
    -0.49
    LOYE
    -0.48
    ↵↵↵↵
    -0.48
     CGFloat
    -0.47
     sendiri
    -0.46
    POSITIVE LOGITS
    enumi
    0.91
    NameInMap
    0.90
    InjectAttribute
    0.89
    UnsafeEnabled
    0.87
    protoimpl
    0.86
    UserScript
    0.85
    AccessorTable
    0.78
     ModelExpression
    0.77
    GraphicsUnit
    0.77
     مرئيه
    0.76
    Activations Density 0.049%

    No Known Activations