Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9381
    Prev
    Next
    INDEX
    Explanations

    terms related to spinal cord injury and its physiological consequences

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

    Referring to the spinal cord

    np_acts-logits-general · gemini-2.0-flash

    spinal cord and nerves

    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
    PerformLayout
    -0.72
     يتيمه
    -0.69
    ennifer
    -0.63
    abestanden
    -0.62
     Aerop
    -0.61
    存于互联网档案馆
    -0.60
     alve
    -0.59
     AEC
    -0.58
     AssemblyProduct
    -0.58
    ToBounds
    -0.57
    POSITIVE LOGITS
     spinal
    1.03
     nerve
    0.95
     Spinal
    0.94
     nerves
    0.83
     Nerve
    0.78
     Nerven
    0.76
    spinal
    0.76
     neuropathy
    0.71
     Rücken
    0.66
     neural
    0.64
    Activations Density 0.600%

    No Known Activations