© 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. 5743
    Prev
    Next
    INDEX
    Explanations

    elements related to singular value decomposition and matrices

    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
     mergeFrom
    -0.60
    SourceChecksum
    -0.50
    AddWithValue
    -0.47
    RenderAtEndOf
    -0.44
    ivably
    -0.43
    nye
    -0.43
     contribution
    -0.42
     campaigns
    -0.42
     campan
    -0.42
    plaid
    -0.41
    POSITIVE LOGITS
     سكانية
    0.74
    +#+#
    0.73
     ujednoznacz
    0.68
    Personensuche
    0.67
    ViewFeatures
    0.65
     Мексичка
    0.65
    లాలు
    0.65
     насељу
    0.62
    TintMode
    0.62
    NameInMap
    0.61
    Activations Density 0.763%

    No Known Activations