© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5338
    Prev
    Next
    INDEX
    Explanations

    references to the '@@' symbol used in code, typically in diff outputs

    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
    BeginContext
    -0.81
     AssemblyTitle
    -0.70
    Autoritní
    -0.61
    ":[{
    -0.54
    expandindo
    -0.53
     ComVisible
    -0.52
    Tembelea
    -0.50
     surla
    -0.50
     esternos
    -0.49
    ینده
    -0.49
    POSITIVE LOGITS
     jsPsych
    1.13
    colgroup
    1.13
    DockStyle
    0.96
     NOI
    0.93
    @@
    0.91
    AutoScale
    0.86
    RegistryLite
    0.78
     saurait
    0.74
    cookieParser
    0.70
    principalColumn
    0.69
    Activations Density 0.032%

    No Known Activations