© 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. 4-GEMMASCOPE-RES-16K
    11. 9797
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and functions related to probability and mathematical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.52
     blanche
    -0.45
    phan
    -0.45
    tor
    -0.45
    tral
    -0.45
     пери
    -0.44
    нер
    -0.44
     manqué
    -0.43
    kai
    -0.43
    pla
    -0.42
    POSITIVE LOGITS
    ReLU
    0.87
     FontWeight
    0.82
     '\\;'
    0.79
     ExecuteAsync
    0.75
     GenerationType
    0.74
    TintMode
    0.73
     setEmail
    0.73
    usermodel
    0.71
     expon
    0.70
    ItemBackground
    0.70
    Activations Density 1.562%

    No Known Activations