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. 92591
    Prev
    Next
    INDEX
    Explanations

    terms related to citizenship and parental rights

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

    citizenship, parenthood, suffixes

    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
     stället
    -0.52
    er
    -0.47
     Externe
    -0.45
    Slf
    -0.44
    Param
    -0.43
    ']){
    -0.43
    Mono
    -0.43
    Don
    -0.43
     république
    -0.43
     createState
    -0.41
    POSITIVE LOGITS
    atorship
    0.95
    orship
    0.91
    anship
    0.90
    thood
    0.86
    ership
    0.84
    manship
    0.84
     betweenstory
    0.77
    ERSHIP
    0.75
    wardship
    0.70
     Ownership
    0.69
    Activations Density 0.013%

    No Known Activations