© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12083
    Prev
    Next
    INDEX
    Explanations

    elements related to Android layout attributes and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sepeda
    -0.36
     contribución
    -0.35
     espíritu
    -0.35
     atracción
    -0.33
     quedado
    -0.30
     Utf
    -0.29
    şı
    -0.29
     curiosidad
    -0.29
    farwyddwr
    -0.28
     kirja
    -0.28
    POSITIVE LOGITS
     '\\;'
    0.92
     &___
    0.86
    parsedMessage
    0.84
     surla
    0.77
    Hentet
    0.75
    @[+][
    0.73
    aarrggbb
    0.72
    PYX
    0.69
     Италијани
    0.63
     kasarigan
    0.62
    Activations Density 0.978%

    No Known Activations