© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 18729
    Prev
    Next
    INDEX
    Explanations

    the beginning of paragraphs or sections in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zulegen
    -0.71
    帯
    -0.65
    '},
    -0.62
    »).
    -0.62
    voorbeeld
    -0.59
     Quinta
    -0.58
     ")
    -0.57
    **
    -0.57
    ≦)
    -0.57
    性が
    -0.57
    POSITIVE LOGITS
    mybatisplus
    1.09
    Билгалдахарш
    0.84
     للمعارف
    0.82
    ward
    0.75
    wards
    0.69
     ModelExpression
    0.68
    __()
    0.66
     समीक्षक
    0.65
    inander
    0.65
     fuori
    0.63
    Activations Density 0.008%

    No Known Activations