© 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. 0-GEMMASCOPE-RES-65K
    11. 12513
    Prev
    Next
    INDEX
    Explanations

    iterations or functions related to the concept of "start" in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.53
    排行榜
    -0.53
     '
    -0.48
    ঞ
    -0.46
     Mati
    -0.46
    ToTable
    -0.46
    klaim
    -0.46
     ?",
    -0.44
     club
    -0.44
     Club
    -0.44
    POSITIVE LOGITS
    start
    0.95
    Start
    0.89
    START
    0.86
     kasarigan
    0.84
     متعلقه
    0.82
    GEBURTSDATUM
    0.81
    RectangleBorder
    0.80
     start
    0.79
     Start
    0.76
     незавершена
    0.75
    Activations Density 0.071%

    No Known Activations