© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15348
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical properties and stress analysis

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

    "max," "maximum," or "load"

    np_acts-logits-general · gemini-2.0-flash

    maximum load or pull

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.61
    neté
    -0.60
    PerformLayout
    -0.58
    EndInit
    -0.58
     groupBox
    -0.58
    abestanden
    -0.57
    XtraReports
    -0.55
    Revenir
    -0.53
     "..\..\..\
    -0.52
     Goodwin
    -0.52
    POSITIVE LOGITS
    bootstrapcdn
    0.77
     max
    0.76
    max
    0.72
     maximum
    0.71
     maksimum
    0.71
     withstand
    0.70
     capacity
    0.67
     rated
    0.67
     maximale
    0.66
    Maximum
    0.66
    Activations Density 0.134%

    No Known Activations