© 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. 14765
    Prev
    Next
    INDEX
    Explanations

    mentions of specific job or employment references

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

    "a" followed by location/organization

    np_acts-logits-general · gemini-2.0-flash

    common nouns and people

    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
    ItemBackground
    -0.73
    PreferredItem
    -0.69
    Становништво
    -0.65
     intptr
    -0.63
    selves
    -0.62
     Reverso
    -0.60
    AnimationsModule
    -0.60
     defStyle
    -0.59
     yourselves
    -0.57
     NSCoder
    -0.57
    POSITIVE LOGITS
     nearby
    0.89
     unnamed
    0.86
     friend
    0.84
     colleague
    0.80
     neighbouring
    0.78
     neighboring
    0.77
     unidentified
    0.75
    nearby
    0.74
     recent
    0.73
     undisclosed
    0.71
    Activations Density 0.432%

    No Known Activations