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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5741
    Prev
    Next
    INDEX
    Explanations

    phrases related to components and their properties in complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toContain
    -0.60
    EndGlobalSection
    -0.60
    AnchorStyles
    -0.60
    InjectAttribute
    -0.58
    FormTagHelper
    -0.58
    apé
    -0.57
    aloo
    -0.57
     colliding
    -0.56
     onCreateView
    -0.55
    numerusform
    -0.55
    POSITIVE LOGITS
    LayoutStyle
    0.47
    gonic
    0.47
    Auswahl
    0.45
    tvguidetime
    0.44
    TabIndex
    0.43
     Universitaria
    0.41
     dom
    0.41
    :✨
    0.39
     Arend
    0.39
     بیرون
    0.39
    Activations Density 1.186%

    No Known Activations