© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14106
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies, clinical outcomes, and experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.92
    OGND
    -0.86
    WireFormatLite
    -0.74
     Italijanski
    -0.74
    клопе
    -0.71
     виправивши
    -0.70
     ویکی‌پدی
    -0.69
    GOTREF
    -0.69
    WebVitals
    -0.67
    ngrx
    -0.67
    POSITIVE LOGITS
     there
    0.86
     they
    0.83
     we
    0.82
     it
    0.75
     she
    0.67
     he
    0.60
     you
    0.55
     the
    0.47
     nothing
    0.46
     neither
    0.45
    Activations Density 0.750%

    No Known Activations