© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3550
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and possessions

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

    Personal pronouns followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners and subsequent nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Personensuche
    -0.76
    Ծանոթ
    -0.66
     decidedly
    -0.66
    ishments
    -0.65
    MemoryWarning
    -0.65
     disambiguazione
    -0.65
    ReusableCell
    -0.65
    הערות
    -0.65
    ponym
    -0.63
    transQ
    -0.59
    POSITIVE LOGITS
     equipments
    0.66
     advices
    0.64
     another
    0.63
    AutoScale
    0.63
     evidences
    0.61
     stuffs
    0.57
     functionalities
    0.56
     each
    0.53
     feedbacks
    0.51
     dialogues
    0.51
    Activations Density 0.172%

    No Known Activations