© 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. 24416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "abstract" and related terms that indicate the presence of abstract sections in documents

    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
     TType
    -0.63
     BorderRadius
    -0.62
    extAlignment
    -0.61
    QtCore
    -0.60
    RunWith
    -0.57
    IGraphics
    -0.56
     Charlie
    -0.55
    ElementAt
    -0.55
     fieldNum
    -0.55
    بوابة
    -0.54
    POSITIVE LOGITS
    abstract
    1.01
     مشين
    0.82
    \{\\
    0.76
    :✨
    0.73
     demurrer
    0.71
    例句
    0.69
    abstractmethod
    0.69
     Josephus
    0.66
    issauga
    0.66
     Bamberg
    0.66
    Activations Density 0.002%

    No Known Activations