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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 12
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "new" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.90
    Rüyada
    -0.74
    WireFormatLite
    -0.73
    ună
    -0.69
    WireFormat
    -0.67
    SourceChecksum
    -0.67
    webElementXpaths
    -0.65
     referenties
    -0.64
    GOTREF
    -0.62
    pegno
    -0.61
    POSITIVE LOGITS
     new
    1.18
    new
    1.05
    New
    0.90
     New
    0.89
     neue
    0.86
     nieuwe
    0.81
     nuova
    0.80
     neuen
    0.79
     новой
    0.77
     nouvelle
    0.75
    Activations Density 0.033%

    No Known Activations