© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1821
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to message handling and updates in a remote process context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.58
    httphttps
    -0.55
    delwed
    -0.52
    transQ
    -0.51
     المعيارى
    -0.48
     متعلقه
    -0.47
    OGND
    -0.47
    acyjnych
    -0.43
     MemoryStream
    -0.42
     Dov
    -0.42
    POSITIVE LOGITS
     rank
    0.69
     MPI
    0.65
    rank
    0.63
    MPI
    0.62
    Ranks
    0.60
    Rank
    0.59
     Rank
    0.57
     ranks
    0.54
    ranks
    0.54
     Ranks
    0.52
    Activations Density 0.322%

    No Known Activations