© 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. 28-GEMMASCOPE-RES-16K
    11. 5402
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific methodologies and experimental conditions

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

    "as" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    as input or basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.46
    ########.
    -0.45
     '\\;'
    -0.44
    AccessorTable
    -0.43
     "..\..\
    -0.40
    dures
    -0.40
     bagay
    -0.39
    RegressionTest
    -0.37
     étoit
    -0.37
    libatkan
    -0.37
    POSITIVE LOGITS
     source
    0.64
     basis
    0.58
     primary
    0.54
     hlavní
    0.52
     unifying
    0.52
     motive
    0.52
     main
    0.52
     głów
    0.50
    主な
    0.50
    source
    0.49
    Activations Density 0.443%

    No Known Activations