© 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. 20-GEMMASCOPE-RES-131K
    11. 119898
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of moving forward or taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.60
     ultraviolet
    -0.57
    Granite
    -0.57
     Granite
    -0.56
    Lamp
    -0.56
    izaje
    -0.56
    URLException
    -0.55
    Fault
    -0.55
    Lig
    -0.54
    Aluminum
    -0.54
    POSITIVE LOGITS
     proceed
    0.82
     PROCEED
    0.75
     Proceed
    0.72
    Proceed
    0.72
     proceedings
    0.68
     proceeding
    0.68
     proceeds
    0.66
    proceed
    0.65
     proceeded
    0.63
     Proceeds
    0.60
    Activations Density 0.013%

    No Known Activations