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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1019
    Prev
    Next
    INDEX
    Explanations

    references to taking action or implementing measures

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

    about taking steps or action

    np_acts-logits-general · gemini-2.0-flash

    taking action or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    slidesToShow
    -0.44
    setHorizontal
    -0.38
     disambiguazione
    -0.38
    URLException
    -0.38
    ARROLL
    -0.38
    ERVIEW
    -0.38
     joaat
    -0.37
    scrollY
    -0.37
     confuses
    -0.37
     BeautifulSoup
    -0.36
    POSITIVE LOGITS
     Maßnahmen
    0.89
     action
    0.85
     actions
    0.79
     Actions
    0.75
     acción
    0.73
    action
    0.72
     Action
    0.71
    Action
    0.71
    IAction
    0.70
     ACTION
    0.69
    Activations Density 0.255%

    No Known Activations