© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 3112
    Prev
    Next
    INDEX
    Explanations

    verbs related to competition and interactions in various contexts

    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
    CppCodeGen
    -0.73
    //
    -0.73
     protoimpl
    -0.69
    TemporalType
    -0.68
    EndProject
    -0.67
    <>("
    -0.66
    UnusedPrivate
    -0.66
    Билгалдахарш
    -0.66
    ",&
    -0.65
     الرياضيه
    -0.62
    POSITIVE LOGITS
     myſelf
    0.83
     away
    0.77
     répondu
    0.76
     foncé
    0.73
     with
    0.71
     itſelf
    0.71
     affich
    0.70
     becauſe
    0.69
     againſt
    0.68
    hésite
    0.67
    Activations Density 0.252%

    No Known Activations