© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16149
    Prev
    Next
    INDEX
    Explanations

    terms related to programming flags and statuses

    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
    PostInfinity
    -0.62
    IVEREF
    -0.59
    expandindo
    -0.57
    клопе
    -0.52
    octanol
    -0.52
    hoodie
    -0.48
    siella
    -0.48
     المعيارى
    -0.47
    oneofs
    -0.47
    ercises
    -0.47
    POSITIVE LOGITS
    resizingMask
    0.69
     resourceCulture
    0.64
    AnchorStyles
    0.63
    routeProvider
    0.62
    AxisAlignment
    0.61
     Autorizaciones
    0.61
    fortawesome
    0.60
    CloseOperation
    0.57
     Schlä
    0.57
    WindowConstants
    0.57
    Activations Density 0.883%

    No Known Activations