© 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. 20-GEMMASCOPE-RES-16K
    11. 15863
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns or values

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

    Non-English (foreign) words

    np_acts-logits-general · gemini-2.0-flash

    code file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rália
    -0.57
    ulties
    -0.54
    PyObject
    -0.52
     dabei
    -0.49
    ²/
    -0.49
    clearInterval
    -0.44
     TType
    -0.42
    Répondre
    -0.42
     Pencil
    -0.42
    assies
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.82
     مرئيه
    0.73
    انيف
    0.71
    Demografia
    0.71
    Portail
    0.71
    expandindo
    0.64
     beginnetje
    0.63
     مشين
    0.62
    tonsoft
    0.61
    findpost
    0.61
    Activations Density 0.022%

    No Known Activations