© 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. 20-GEMMASCOPE-RES-16K
    11. 6079
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated terms indicating ownership or relation

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

    family relationship terms like "his", "her", "wife", "son", "father", etc.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    possessive markers—both pronouns and the genitive ’s—that indicate ownership or relational belonging.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    possessive pronouns and possessive clitics ('s) indicating ownership or association

    oai_token-act-pair · deepseek-r1Triggered by @jyhe0408

    possessive references indicating family relationships or close personal connections.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Following
    -0.40
    worpen
    -0.40
    ,:);
    -0.40
    FontOfSize
    -0.39
     passage
    -0.38
    weetened
    -0.38
     campur
    -0.37
     pamoja
    -0.37
    Following
    -0.37
    Hochspringen
    -0.37
    POSITIVE LOGITS
     sister
    0.65
     colleagues
    0.60
     peers
    0.60
     fellow
    0.57
     teammates
    0.54
     friends
    0.54
     colleague
    0.52
     collega
    0.52
     brother
    0.51
     classmates
    0.49
    Activations Density 0.190%

    No Known Activations