© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9257
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and dynamics

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

    family and relatives

    np_acts-logits-general · gemini-2.0-flash

    family and relationships

    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
     للمعارف
    -0.46
    GEBURTSDATUM
    -0.43
    ixante
    -0.43
    KURZBESCHREIBUNG
    -0.41
    Билгалдахарш
    -0.40
     artykuł
    -0.39
    Vidite
    -0.38
     يتيمه
    -0.37
    VYMaps
    -0.37
     assertion
    -0.36
    POSITIVE LOGITS
    family
    0.75
     family
    0.74
     keluarga
    0.69
    Family
    0.68
     families
    0.65
    FAMILY
    0.64
    ViewFeatures
    0.64
     Family
    0.63
     famille
    0.61
     FAMILY
    0.61
    Activations Density 0.228%

    No Known Activations