© 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. 10-GEMMASCOPE-RES-16K
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    concepts related to wear and erosion of materials or surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.82
     kaarangay
    -0.79
    MemoryWarning
    -0.76
     autorytatywna
    -0.66
    httphttps
    -0.66
    #+#
    -0.65
     SwitchCompat
    -0.64
     BoxDecoration
    -0.63
     للمعارف
    -0.62
    BagConstraints
    -0.62
    POSITIVE LOGITS
     decay
    0.76
     corrosion
    0.72
     erosion
    0.66
     desgaste
    0.66
     decaying
    0.65
    decay
    0.64
     deterioration
    0.64
     worn
    0.63
     erode
    0.62
     decays
    0.61
    Activations Density 0.483%

    No Known Activations