© 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. 24-GEMMASCOPE-RES-16K
    11. 10386
    Prev
    Next
    INDEX
    Explanations

    references to heavy metals and their ecological impact

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

    Metals, elements, or excessive nutrients

    np_acts-logits-general · gemini-2.0-flash

    trace metals and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grafen
    -0.50
     חיצוניים
    -0.50
     fatte
    -0.49
     abriu
    -0.49
    forName
    -0.48
     McAllister
    -0.48
     ग्राहक
    -0.47
    jší
    -0.47
    ViewStyle
    -0.47
    HtmlAttribute
    -0.46
    POSITIVE LOGITS
     speciation
    0.75
     trace
    0.72
     metals
    0.71
     metal
    0.71
     Trace
    0.69
     mobility
    0.67
     element
    0.66
     concentrations
    0.65
     elemental
    0.65
    metals
    0.65
    Activations Density 0.626%

    No Known Activations