© 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. 30-GEMMASCOPE-RES-16K
    11. 11213
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and biological measurements

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

    technical/scientific terms

    np_acts-logits-general · gemini-2.0-flash

    indicator, pulses, region, port, network, environment, phenomena, method, combination, velocity, staining, genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.54
     propOrder
    -0.52
    ][]
    -0.39
    ⤹
    -0.38
    Попис
    -0.35
    참고
    -0.35
    umbing
    -0.35
    NameInMap
    -0.34
    عرِّف
    -0.33
     Roskov
    -0.33
    POSITIVE LOGITS
     which
    0.62
     firstly
    0.57
     belongs
    0.55
     οποία
    0.54
     nowadays
    0.54
     GenerationType
    0.51
     methode
    0.49
     Firstly
    0.49
     sûrement
    0.49
     belong
    0.48
    Activations Density 1.665%

    No Known Activations