© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13951
    Prev
    Next
    INDEX
    Explanations

    terminology related to hearing loss and associated disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.43
     onAnimation
    -0.43
    FailureListener
    -0.41
     wireType
    -0.40
     ویکی‌پدی
    -0.40
    Cubit
    -0.39
     pole
    -0.37
    PCell
    -0.37
    phorbia
    -0.37
     createSlice
    -0.36
    POSITIVE LOGITS
     hearing
    1.29
     Hearing
    1.16
    Hearing
    1.14
    hearing
    1.05
     HEARING
    1.02
    HEARING
    0.79
     coch
    0.79
     Hear
    0.78
     tinnitus
    0.76
     deafness
    0.75
    Activations Density 0.362%

    No Known Activations