© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8672
    Prev
    Next
    INDEX
    Explanations

    components and features related to cushioning and support in various objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Soft, swollen masses or fillings

    np_acts-logits-general · gemini-2.0-flash

    filled volume or soft mass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dö
    -0.37
     aço
    -0.36
     vitesse
    -0.35
    addColumn
    -0.35
    getSystem
    -0.34
     fjor
    -0.33
     légal
    -0.33
    :✨
    -0.33
     inoxydable
    -0.33
    CharStream
    -0.32
    POSITIVE LOGITS
     LUMP
    0.77
     cushion
    0.76
     squishy
    0.73
     inflated
    0.73
     stuffed
    0.71
     plush
    0.69
    stuffed
    0.68
     cushions
    0.68
     BorderRadius
    0.66
    lump
    0.66
    Activations Density 0.847%

    No Known Activations