© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 115087
    Prev
    Next
    INDEX
    Explanations

    terms related to familial relationships, specifically those indicating great-grandparents and grand-family ties

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

    family generations

    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
    parsedMessage
    -0.87
    IContainer
    -0.83
    __(/*!
    -0.80
    exitRule
    -0.77
     propOrder
    -0.75
     AssemblyTitle
    -0.74
    IntoConstraints
    -0.73
    ագրություններ
    -0.69
     الرياضيه
    -0.69
     surla
    -0.69
    POSITIVE LOGITS
    räck
    0.32
     vérification
    0.30
    代
    0.28
     directos
    0.28
     réforme
    0.27
     manualidades
    0.26
     Diarsipkan
    0.26
    foglal
    0.26
    grunns
    0.26
     vård
    0.26
    Activations Density 0.001%

    No Known Activations