© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 4291
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and related first-person expressions

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

    I you pronouns

    np_acts-logits-general · gemini-2.5-flash-lite

    direct address and personal references in conversational text, including first- and second-person pronouns and user handles.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    الحياه
    -0.62
    EnableWeb
    -0.55
     Stoll
    -0.51
    таратура
    -0.50
    akterysty
    -0.48
    ModelAdmin
    -0.48
    ::$_
    -0.47
    XmlRootElement
    -0.47
     useCallback
    -0.46
     bertindak
    -0.45
    POSITIVE LOGITS
     ब्रेकडाउन
    0.48
    SharedCtor
    0.47
     للاسماء
    0.41
     ModelExpression
    0.40
    InjectAttribute
    0.40
     defaultstate
    0.38
    IsMutable
    0.32
     defStyleAttr
    0.32
     Bakter
    0.32
    tanleria
    0.31
    Activations Density 0.001%

    No Known Activations