© 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. 9-GEMMASCOPE-RES-16K
    11. 14574
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and references related to physical and biological phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.97
    Datuak
    -0.79
    期刊论文
    -0.72
    NUMX
    -0.71
    ărat
    -0.69
    orteur
    -0.68
    mability
    -0.66
    "):
    -0.65
    igshid
    -0.65
    }{*}{}
    -0.64
    POSITIVE LOGITS
    ึ้น
    0.56
     buurt
    0.55
     miglia
    0.55
     spørs
    0.55
     illet
    0.53
     lleve
    0.53
     mė
    0.52
    XmlRootElement
    0.52
     llevará
    0.52
     parha
    0.51
    Activations Density 0.291%

    No Known Activations