Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10472
    Prev
    Next
    INDEX
    Explanations

    terms related to health and wellness, particularly nutrients and their effects on the body

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mekte
    -0.54
    kon
    -0.50
     ggf
    -0.48
    X
    -0.48
     ligiloj
    -0.48
    ستار
    -0.48
     öner
    -0.48
     Wissenschaften
    -0.47
    IP
    -0.47
    (
    -0.47
    POSITIVE LOGITS
    BagConstraints
    0.70
    makeText
    0.70
     lenker
    0.65
    ientí
    0.65
    ^(@)
    0.65
     وتسجيلات
    0.64
    BASEPATH
    0.64
     Akismet
    0.64
    PMailer
    0.63
    TypedDataSet
    0.63
    Activations Density 0.685%

    No Known Activations