© 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. 7713
    Prev
    Next
    INDEX
    Explanations

    token sequence patterns that begin with a specific start token

    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
     is
    -0.73
     was
    -0.71
     itself
    -0.67
     Verhält
    -0.60
     Verfahrens
    -0.57
    äinen
    -0.56
     commerciales
    -0.56
    idis
    -0.55
    escens
    -0.54
     does
    -0.53
    POSITIVE LOGITS
     themselves
    0.83
     jotka
    0.81
    themselves
    0.75
     obstante
    0.73
     αυτά
    0.71
     those
    0.68
    those
    0.67
     PartialEq
    0.67
    ofluor
    0.66
     مختلف
    0.65
    Activations Density 0.018%

    No Known Activations