© 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. 4-GEMMASCOPE-RES-16K
    11. 9688
    Prev
    Next
    INDEX
    Explanations

    references to premium quality products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __()
    -0.70
    RenderAtEndOf
    -0.65
    Slf
    -0.64
     Maarten
    -0.63
    balenciaga
    -0.63
    lossians
    -0.62
    زب
    -0.62
    /*
    -0.62
     vtk
    -0.61
    fhir
    -0.61
    POSITIVE LOGITS
     premium
    2.68
    premium
    2.48
     Premium
    2.45
    Premium
    2.37
     premiums
    2.11
     PREMIUM
    2.10
    PREMI
    1.71
     Premi
    1.57
    プレミアム
    1.45
     プレミアム
    1.28
    Activations Density 0.071%

    No Known Activations