© 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. 14667
    Prev
    Next
    INDEX
    Explanations

    references to rankings or hierarchical positions

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

    Tokens followed by "rank"

    np_acts-logits-general · gemini-2.0-flash

    rank order

    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
    verwijspagina
    -0.57
    FML
    -0.49
    bB
    -0.48
    YesNo
    -0.47
    /*
    -0.47
    ように
    -0.46
    ⎩
    -0.46
     endTime
    -0.45
     esternos
    -0.45
    ओं
    -0.45
    POSITIVE LOGITS
    قایناقلار
    0.90
     RANK
    0.84
    Personendaten
    0.82
    RANK
    0.77
    :✨
    0.76
    BlockingQueue
    0.71
     Ranks
    0.70
     ranks
    0.69
     Rank
    0.69
    Rank
    0.69
    Activations Density 0.084%

    No Known Activations