© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5972
    Prev
    Next
    INDEX
    Explanations

    features related to numbers and mathematical operations

    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
     Majefty
    -0.79
     Houſe
    -0.76
     Theſe
    -0.75
     pleaſure
    -0.73
     houſe
    -0.72
     Monfieur
    -0.72
     enfans
    -0.71
    GEBURTSDATUM
    -0.70
     leſs
    -0.68
     himſelf
    -0.68
    POSITIVE LOGITS
     المعيارى
    0.87
    mybatisplus
    0.65
     esternos
    0.63
    ftagPool
    0.62
    ViewImports
    0.61
    !*\
    0.59
    /*
    0.55
    awtextra
    0.55
    lwjgl
    0.53
     ComVisible
    0.53
    Activations Density 0.301%

    No Known Activations