© 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. 0-GEMMASCOPE-RES-65K
    11. 10665
    Prev
    Next
    INDEX
    Explanations

    instances of redirection and references to the term "Blu"

    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
    
    -0.73
     beginnetje
    -0.69
     vouloir
    -0.61
    Демографія
    -0.58
    Rogers
    -0.57
     auroit
    -0.55
     كورة
    -0.54
    noční
    -0.53
     Rogers
    -0.52
    حياتها
    -0.52
    POSITIVE LOGITS
     redirected
    0.83
     directed
    0.79
    directed
    0.71
     Vul
    0.70
     redirect
    0.68
     dirigida
    0.67
    setScene
    0.67
    segue
    0.66
     Redirect
    0.65
     Directed
    0.65
    Activations Density 0.070%

    No Known Activations