© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 6360
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grandkids
    -1.05
     grandchildren
    -0.95
    grandchildren
    -0.86
     EconPapers
    -0.78
     grandchild
    -0.73
     wives
    -0.69
     spouses
    -0.67
     Spouse
    -0.66
     disambiguazione
    -0.65
    Parent
    -0.62
    POSITIVE LOGITS
     male
    0.66
    QMetaType
    0.66
     older
    0.62
     female
    0.61
     middle
    0.60
     contextLoads
    0.58
     oldest
    0.58
    oredCriteria
    0.58
     elder
    0.56
    ֹת
    0.56
    Activations Density 0.147%

    No Known Activations