© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5476
    Prev
    Next
    INDEX
    Explanations

    references to water dynamics in ecological systems

    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
     utafitiHapana
    -0.54
    PyExc
    -0.51
     BoxFit
    -0.48
     AssemblyCulture
    -0.47
     wireType
    -0.46
    AddTagHelper
    -0.44
    addContainerGap
    -0.44
    ArrowToggle
    -0.44
    initComponents
    -0.43
     jLabel
    -0.42
    POSITIVE LOGITS
     groundwater
    0.96
     aquifers
    0.88
    地下
    0.88
     aquifer
    0.87
     underground
    0.86
     recharge
    0.82
     Groundwater
    0.80
     subterrá
    0.80
     Underground
    0.79
    Groundwater
    0.77
    Activations Density 0.254%

    No Known Activations