Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10488
    Prev
    Next
    INDEX
    Explanations

    technical terms related to numerical simulation and computational methods

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

    Numerical methods and time-stepping

    np_acts-logits-general · gemini-2.0-flash

    numerical methods, adaptive time-stepping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.57
    windowFixed
    -0.54
    YOND
    -0.54
     gaga
    -0.47
     незавершена
    -0.47
     &___
    -0.47
    ArrowToggle
    -0.46
    Andi
    -0.45
    XOR
    -0.45
     surla
    -0.45
    POSITIVE LOGITS
     discretization
    0.94
     discre
    0.87
     mesh
    0.85
     Numerical
    0.79
     numerical
    0.79
     Courant
    0.78
     Discre
    0.77
    discre
    0.75
    Discre
    0.73
     numérique
    0.72
    Activations Density 1.205%

    No Known Activations