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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 873
    Prev
    Next
    INDEX
    Explanations

    keywords related to children and societal structures and institutions

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

    child, media, law, history, courts, railway

    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-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
     Roskov
    -0.59
    GEBURTSDATUM
    -0.57
    PYX
    -0.55
    OCCURRED
    -0.54
    InitVars
    -0.52
     ویکی‌پدیا
    -0.51
     يتيمه
    -0.49
    OGND
    -0.49
     szk
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
     residents
    0.54
    Residents
    0.47
     Residents
    0.47
    residents
    0.46
    weds
    0.42
     locu
    0.41
     propOrder
    0.40
     inhabitants
    0.40
     natives
    0.39
     habitants
    0.39
    Activations Density 0.412%

    No Known Activations