© 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 - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11463
    Prev
    Next
    INDEX
    Explanations

    references to machine learning concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daß
    -0.95
    faßt
    -0.82
     Einfluß
    -0.79
     idéia
    -0.75
    
    -0.74
     biß
    -0.72
     muß
    -0.70
     Schluß
    -0.67
     really
    -0.66
    いろいろな
    -0.66
    POSITIVE LOGITS
     leveraging
    0.93
     Notably
    0.89
     incentiv
    0.83
    <>());
    0.83
     Importantly
    0.82
     impactful
    0.79
    WithIOException
    0.77
     onboarding
    0.76
     microbiome
    0.76
     overarching
    0.75
    Activations Density 2.954%

    No Known Activations