© 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. 10-GEMMASCOPE-RES-16K
    11. 11723
    Prev
    Next
    INDEX
    Explanations

    keywords related to the processes of creating, generating, or modifying data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    yntaxException
    -0.56
     kaarangay
    -0.50
    хьтан
    -0.47
     disambiguazione
    -0.46
    DockStyle
    -0.45
    AnchorStyles
    -0.43
     purpoſe
    -0.43
    Portail
    -0.43
    ViewImports
    -0.42
    ToProps
    -0.41
    POSITIVE LOGITS
    tered
    0.69
    cted
    0.67
    rafted
    0.67
    aced
    0.67
    inated
    0.66
    acted
    0.66
    played
    0.65
    keted
    0.65
    outed
    0.65
    ressed
    0.65
    Activations Density 1.671%

    No Known Activations