© 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. 22-GEMMASCOPE-RES-16K
    11. 3859
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to network protocols and data transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.93
     utafitiHapana
    -0.88
     препратки
    -0.86
     للاسماء
    -0.81
    RTLI
    -0.79
    VYMaps
    -0.74
     externi
    -0.74
     intStringLen
    -0.73
    <unused51>
    -0.71
    <unused52>
    -0.71
    POSITIVE LOGITS
     reves
    0.33
     temperature
    0.33
    <eos>
    0.31
    SuppressLint
    0.31
     treatment
    0.30
     time
    0.29
    eventId
    0.29
     moda
    0.28
     introduced
    0.28
     useState
    0.28
    Activations Density 4.084%

    No Known Activations