© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1660
    Prev
    Next
    INDEX
    Explanations

    references to individuals and collective pronouns in questions or discussions

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

    "Anyone," "someone," or "who" at the start of a question

    np_acts-logits-general · gemini-2.0-flash

    anyone else or someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UVWXYZ
    -0.88
    Datuak
    -0.88
     EconPapers
    -0.84
     Мексичка
    -0.83
     lenker
    -0.81
    __.__
    -0.78
    ConstraintMaker
    -0.78
     kaarangay
    -0.77
    Manbalar
    -0.77
     ivelany
    -0.76
    POSITIVE LOGITS
     else
    2.11
    else
    1.17
     ELSE
    1.14
     Else
    1.14
    Else
    1.14
     who
    1.14
    ELSE
    0.91
     kto
    0.74
    who
    0.64
     anders
    0.64
    Activations Density 0.100%

    No Known Activations