© 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. 20-GEMMASCOPE-RES-16K
    11. 8583
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Pra" in various forms and contexts

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

    starting with "pra" or "practi"

    np_acts-logits-general · gemini-2.0-flash

    pra-, practi- prefixes followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chb
    -0.52
    تفصیلات
    -0.51
     bianchi
    -0.49
    GUILayout
    -0.49
    võ
    -0.49
     Fat
    -0.49
    (?
    -0.49
     Lutz
    -0.48
     Meri
    -0.48
    INGO
    -0.47
    POSITIVE LOGITS
    BeginContext
    0.72
     IActionResult
    0.71
    aarrggbb
    0.69
    出版年
    0.68
    GraphicsUnit
    0.67
    IntoConstraints
    0.66
    Vidite
    0.66
     contextLoads
    0.64
     ligiloj
    0.64
     الرياضيه
    0.63
    Activations Density 0.081%

    No Known Activations