© 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 EvalsExportsAPI 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. 22013
    Prev
    Next
    INDEX
    Explanations

    references to legal actions, motions, or lawsuits

    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
     conosce
    -0.47
    tadır
    -0.47
    tabControl
    -0.45
    ⓧ
    -0.45
    rsiniz
    -0.44
     svolge
    -0.44
    turnstile
    -0.41
     dispozici
    -0.41
     Aun
    -0.41
     Roskov
    -0.40
    POSITIVE LOGITS
     AttributeSet
    0.75
    styleUrls
    0.71
    webElementXpaths
    0.67
    RepeatedField
    0.66
     DialogInterface
    0.65
     esternos
    0.64
     outraged
    0.61
     MainAxisSize
    0.61
    MouseListener
    0.61
    RetentionPolicy
    0.61
    Activations Density 0.097%

    No Known Activations