© 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. 20-GEMMASCOPE-RES-16K
    11. 11564
    Prev
    Next
    INDEX
    Explanations

    terms related to card game mechanics and control structures

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

    Values of variables (e.g., booleans, integers)

    np_acts-logits-general · gemini-2.0-flash

    control finished/failed, player mark, wave start, success/fail

    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
    بوابة
    -0.67
     XNUMX
    -0.66
    ishments
    -0.59
     كومونز
    -0.59
    MenuInflater
    -0.58
    Hentet
    -0.57
     encompassing
    -0.55
    ']/
    -0.54
     ་་
    -0.54
    '],'
    -0.54
    POSITIVE LOGITS
    operate
    0.75
    remain
    0.72
    StructEnd
    0.70
     confuse
    0.68
     AssemblyCulture
    0.67
     recommand
    0.66
    succeed
    0.66
     Operate
    0.65
     belong
    0.65
    Infor
    0.64
    Activations Density 0.276%

    No Known Activations