© 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. 19-GEMMASCOPE-RES-16K
    11. 15089
    Prev
    Next
    INDEX
    Explanations

    programmatic conditions and logical structures involving function execution and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.65
     useDispatch
    -0.55
    often
    -0.54
    Typical
    -0.52
     often
    -0.52
     Often
    -0.51
    much
    -0.49
     debates
    -0.49
     ideas
    -0.48
     spesso
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.70
     either
    0.69
     previously
    0.68
     valid
    0.64
    자가
    0.62
     alguno
    0.62
     alguma
    0.62
     somebody
    0.61
     signalled
    0.61
    either
    0.61
    Activations Density 0.843%

    No Known Activations