© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 13309
    Prev
    Next
    INDEX
    Explanations

    references to kinship and personal relationships in linguistic contexts

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

    Pronouns, person references, and implied subjects

    np_acts-logits-general · gemini-2.0-flash

    person reference and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -0.47
    المناصب
    -0.43
    fillType
    -0.43
    ftagPool
    -0.40
     Laj
    -0.40
     MCA
    -0.38
     DAF
    -0.38
    AnimationsModule
    -0.38
    テンツ
    -0.37
    oader
    -0.36
    POSITIVE LOGITS
     pronouns
    1.08
     pronoun
    1.01
     pronom
    0.79
    Pron
    0.71
    pron
    0.68
     Pron
    0.62
     ngôi
    0.57
     NARR
    0.56
     narrator
    0.55
    Narrator
    0.54
    Activations Density 0.137%

    No Known Activations