© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2007
    Prev
    Next
    INDEX
    Explanations

    statements of intent or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Aims" or "aimed" followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    states the purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.86
     חיצוניים
    -0.79
     AssemblyCulture
    -0.76
     manquer
    -0.66
    ftagPool
    -0.63
     مشين
    -0.61
     NSError
    -0.59
     виправивши
    -0.56
    شهاد
    -0.55
    تقاوى
    -0.55
    POSITIVE LOGITS
     mulia
    0.68
     aims
    0.66
     twofold
    0.64
     möglichst
    0.64
     simple
    0.62
     ultimately
    0.62
     primarily
    0.61
     improving
    0.58
     improve
    0.58
    あくまで
    0.57
    Activations Density 0.208%

    No Known Activations