© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13293
    Prev
    Next
    INDEX
    Explanations

    phrases that include the term "unlikely" and words related to geometric concepts or formulations

    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
    aspectj
    -0.82
    iastes
    -0.81
    intenant
    -0.78
    enoord
    -0.71
     autorytatywna
    -0.71
     jsPsych
    -0.69
     viewDidLoad
    -0.69
    ftagPool
    -0.66
    seguida
    -0.66
    Климат
    -0.64
    POSITIVE LOGITS
     complexity
    0.75
     variety
    0.70
    GraphicsUnit
    0.69
     implementation
    0.59
     complex
    0.57
     Sams
    0.56
     complexities
    0.55
     formulation
    0.54
     Robinson
    0.53
     product
    0.53
    Activations Density 0.064%

    No Known Activations