© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10602
    Prev
    Next
    INDEX
    Explanations

    terms related to spinal cord injuries and rehabilitation

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

    Spinal cord injuries and paralysis

    np_acts-logits-general · gemini-2.0-flash

    spinal cord injury paralysis wheelchair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.51
     متعلقه
    -0.47
     inmediato
    -0.45
    .*")]
    -0.44
     HasFactory
    -0.42
     stanovnika
    -0.41
     escuchado
    -0.40
     ""],
    -0.40
    endpush
    -0.39
     unknownFields
    -0.39
    POSITIVE LOGITS
     wheelchair
    0.71
     paralysis
    0.63
     paralyzed
    0.63
     spinal
    0.61
     paraly
    0.60
     wheelchairs
    0.60
     Wheelchair
    0.59
    GEBURTSDATUM
    0.58
     Spinal
    0.58
     coma
    0.56
    Activations Density 0.322%

    No Known Activations