© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "common" in various contexts

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

    common denominator

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     GenerationType
    -0.65
     Staates
    -0.53
     Aéroport
    -0.51
     Turquía
    -0.50
    iermark
    -0.50
    TypedDataSet
    -0.49
    igurumi
    -0.49
     ModelAndView
    -0.47
    ritz
    -0.47
     matrícula
    -0.47
    POSITIVE LOGITS
     Common
    1.12
     common
    1.11
    Common
    1.09
    common
    1.03
     COMMON
    0.94
    COMMON
    0.83
    CommonModule
    0.80
     común
    0.79
     CommonModule
    0.77
     comum
    0.75
    Activations Density 0.063%

    No Known Activations