© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2524
    Prev
    Next
    INDEX
    Explanations

    metrics related to the validity and reliability of medical measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.73
    ]")]
    -0.66
    GOTREF
    -0.63
    parsedMessage
    -0.61
    ItemBackground
    -0.61
    Personensuche
    -0.60
    期刊论文
    -0.59
    MethodManager
    -0.57
     autorytatywna
    -0.56
    MLLoader
    -0.56
    POSITIVE LOGITS
    %
    0.51
     %
    0.49
     percent
    0.47
     taux
    0.45
    percent
    0.45
     tinggi
    0.44
    \%
    0.43
     percentage
    0.43
    percentage
    0.42
     Prozent
    0.42
    Activations Density 1.414%

    No Known Activations