© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9737
    Prev
    Next
    INDEX
    Explanations

    references to the Google APIs and mentions of indications or results from studies

    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
     GenerationType
    -0.80
    Espèce
    -0.66
    GEBURTSDATUM
    -0.66
    ษา
    -0.66
     larmes
    -0.61
     createSlice
    -0.57
    IntoConstraints
    -0.57
    انيف
    -0.57
     onPage
    -0.56
     palsu
    -0.56
    POSITIVE LOGITS
     denote
    0.72
     chiff
    0.72
     indicated
    0.71
     smoothies
    0.69
     Uber
    0.68
     uber
    0.67
     indicate
    0.66
     #%
    0.65
     disclosing
    0.64
    nikahan
    0.63
    Activations Density 0.082%

    No Known Activations