© 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. 37-GEMMASCOPE-RES-16K
    11. 4553
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of reports and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reported
    -0.79
     reported
    -0.77
    reported
    -0.74
     Reported
    -0.71
    Reports
    -0.70
     Reports
    -0.65
    reports
    -0.65
    Report
    -0.64
     reports
    -0.64
    REPORT
    -0.61
    POSITIVE LOGITS
    orial
    0.69
    NameInMap
    0.59
     card
    0.57
    WebVitals
    0.56
    exitRule
    0.54
     Card
    0.51
    featureID
    0.50
     Cardoso
    0.50
    card
    0.46
    ORIAL
    0.46
    Activations Density 0.104%

    No Known Activations