© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7459
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "cross" in various contexts, particularly in scientific and statistical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.36
    igil
    -0.34
    ViewFeatures
    -0.32
    */].
    -0.32
     Haupts
    -0.31
     ورو
    -0.31
    머
    -0.31
    routeProvider
    -0.30
    GetInstance
    -0.29
     нрави
    -0.29
    POSITIVE LOGITS
     cross
    1.28
    Cross
    1.23
     Cross
    1.23
     CROSS
    1.20
    cross
    1.19
    CROSS
    1.11
     crosses
    0.89
     cros
    0.86
     crossing
    0.85
    crossing
    0.85
    Activations Density 0.078%

    No Known Activations