© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2380
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "common" and its variations in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerToggle
    -0.71
     StatefulWidget
    -0.67
    SourceChecksum
    -0.64
    DeleteBehavior
    -0.61
    tréal
    -0.56
    EndGlobalSection
    -0.56
     capital
    -0.56
    contentLoaded
    -0.54
    StoryboardSegue
    -0.54
    ArrayAdapter
    -0.53
    POSITIVE LOGITS
    common
    1.58
    COMMON
    1.34
    Common
    1.32
     Common
    1.18
     COMMON
    1.16
    commons
    1.10
     common
    0.97
     commons
    0.92
    Commons
    0.92
     المعيارى
    0.86
    Activations Density 0.138%

    No Known Activations