© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2666
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.94
    featureID
    -0.89
    offsetof
    -0.87
     архивлан
    -0.81
     يتيمه
    -0.77
    adpleegd
    -0.73
    SuppressMessage
    -0.73
    IonicModule
    -0.72
     EClass
    -0.72
    AnchorTagHelper
    -0.71
    POSITIVE LOGITS
    ="
    0.73
     colspan
    0.63
    Bronnen
    0.56
    catel
    0.54
    MLElement
    0.53
     Hamb
    0.53
    ="-
    0.50
     cleats
    0.50
    {#
    0.49
    ومت
    0.48
    Activations Density 0.010%

    No Known Activations