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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3668
    Prev
    Next
    INDEX
    Explanations

    discourses around parenting and disciplinary practices

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

    Terms related to discipline or punishment

    np_acts-logits-general · gemini-2.0-flash

    discipline and punishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solidari
    -0.35
     boden
    -0.35
     avocat
    -0.35
     congrès
    -0.34
     plundered
    -0.34
     naveg
    -0.34
     coincid
    -0.33
    ckså
    -0.33
     lobby
    -0.33
    adalajara
    -0.33
    POSITIVE LOGITS
     discipl
    1.16
     discipline
    1.12
     Discipline
    0.99
     disciplinary
    0.97
    Discipline
    0.94
    discipline
    0.91
     punishments
    0.90
     Discipl
    0.88
     disciplina
    0.87
     punishment
    0.85
    Activations Density 0.475%

    No Known Activations