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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 83388
    Prev
    Next
    INDEX
    Explanations

    references to ditches, grooves, and trenches, particularly in the context of construction or topography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ground depressions and openings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    setVerticalGroup
    -0.59
    EndInit
    -0.49
     otomatig
    -0.48
    fromnode
    -0.48
    참고
    -0.47
    DataSetChanged
    -0.47
    EDEFAULT
    -0.46
     فريبيس
    -0.46
    ResumeLayout
    -0.45
    setupUi
    -0.45
    POSITIVE LOGITS
     ditch
    0.93
     pits
    0.85
     trough
    0.83
     pit
    0.82
     gutter
    0.78
     Ditch
    0.77
     trench
    0.76
     ravine
    0.75
     furrow
    0.73
     trenches
    0.71
    Activations Density 0.035%

    No Known Activations