© 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. 23-GEMMASCOPE-RES-16K
    11. 9497
    Prev
    Next
    INDEX
    Explanations

    references to a specific dataset or model

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ámico
    -0.32
    iodía
    -0.30
     cancha
    -0.30
     intenciones
    -0.29
    Localized
    -0.29
     quisiera
    -0.29
     löst
    -0.28
    arch
    -0.28
    localized
    -0.28
    use
    -0.28
    POSITIVE LOGITS
    windowFixed
    0.78
    GEBURTSDATUM
    0.78
    +#+#
    0.76
    ValueStyle
    0.75
    EndInit
    0.75
    MigrationBuilder
    0.74
    FormTagHelper
    0.74
     CreateTagHelper
    0.74
     виправивши
    0.71
    MethodManager
    0.69
    Activations Density 0.888%

    No Known Activations