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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53465
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "set", indicating actions related to configuration or assignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     randomNumber
    -0.52
    tabIndex
    -0.50
     onClose
    -0.50
     currentPage
    -0.49
    olella
    -0.48
     jsonArray
    -0.48
    childNodes
    -0.45
     eventId
    -0.45
    readInt
    -0.45
    ٬
    -0.45
    POSITIVE LOGITS
    set
    0.94
    <bos>
    0.87
    get
    0.62
     set
    0.60
     AssemblyCulture
    0.56
    "]=
    0.55
    barung
    0.47
    SharedDtor
    0.47
     choisi
    0.47
    Set
    0.46
    Activations Density 0.011%

    No Known Activations