© 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. 18-GEMMASCOPE-RES-16K
    11. 1938
    Prev
    Next
    INDEX
    Explanations

    queries related to purchasing healthcare products online

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

    Followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    blackjack surrender, writing jobs, films scored, National Institutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.83
     الحره
    -0.78
    ConstraintMaker
    -0.72
    ValueStyle
    -0.68
    存于互联网档案馆
    -0.62
    WriteBarrier
    -0.62
    //
    -0.60
    modelBuilder
    -0.57
    ServletConfig
    -0.55
    InjectAttribute
    -0.55
    POSITIVE LOGITS
    டன்
    0.52
    umumkan
    0.52
    byes
    0.51
    illaries
    0.48
     caufe
    0.47
     хотела
    0.47
     USS
    0.46
     צילום
    0.45
    vieran
    0.45
    Hogyan
    0.44
    Activations Density 0.016%

    No Known Activations