© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9575
    Prev
    Next
    INDEX
    Explanations

    words associated with sound, particularly onomatopoeic words and descriptors of noise

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

    Two-letter prefix

    np_acts-logits-general · gemini-2.0-flash

    initial sounds followed by word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.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
     للمعارف
    -0.77
     poveznice
    -0.74
    httphttps
    -0.73
     跳转至
    -0.69
     AspNetCore
    -0.65
    ="@+
    -0.63
     חיצוניים
    -0.62
     precisely
    -0.61
    Demografía
    -0.61
    Naissance
    -0.60
    POSITIVE LOGITS
    ppy
    0.49
    ppery
    0.47
    ggle
    0.47
    pping
    0.47
    gg
    0.47
    key
    0.45
    ppig
    0.45
    Ck
    0.45
    iiiiiiii
    0.44
    unch
    0.44
    Activations Density 0.247%

    No Known Activations