© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8560
    Prev
    Next
    INDEX
    Explanations

    components and mechanisms related to mechanical systems, particularly those involving rotating elements and axes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.68
     '\\;'
    -0.58
    kháu
    -0.52
    hysema
    -0.51
    crapers
    -0.49
    IGraphics
    -0.49
     esternos
    -0.48
    $_['
    -0.48
     وتسجيلات
    -0.47
    ########.
    -0.47
    POSITIVE LOGITS
     axis
    0.56
    轴
    0.43
     Zentrum
    0.43
    pivot
    0.42
     axle
    0.42
     axles
    0.41
    軸
    0.41
     Axis
    0.41
    axis
    0.40
    zinho
    0.40
    Activations Density 0.717%

    No Known Activations