© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9994
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts surrounding uncertainties and ambiguities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    duğu
    -0.45
     pobreza
    -0.42
    banyak
    -0.41
     Erfüllung
    -0.40
     poverty
    -0.40
     Прави
    -0.39
     händer
    -0.39
    )))))
    -0.39
     Poverty
    -0.38
     kö
    -0.38
    POSITIVE LOGITS
     Any
    0.98
     any
    0.97
     فريبيس
    0.92
    Any
    0.89
     noDo
    0.88
     whatsoever
    0.87
     Wikimedijinoj
    0.85
    thâu
    0.81
    WebElementEntity
    0.80
     NSCoder
    0.79
    Activations Density 0.291%

    No Known Activations