© 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. 2-GEMMASCOPE-RES-16K
    11. 12900
    Prev
    Next
    INDEX
    Explanations

    mentions of the element molybdenum and its compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moral
    -0.46
    Moral
    -0.42
     Morgan
    -0.42
    UnusedPrivate
    -0.40
     Morality
    -0.39
    atoday
    -0.38
     Morgen
    -0.38
     Moran
    -0.37
    ViewFeatures
    -0.37
     moral
    -0.37
    POSITIVE LOGITS
     mo
    3.14
     Mo
    2.69
    Mo
    2.67
    mo
    2.59
     MO
    2.16
    MO
    2.06
     мо
    1.74
     Mox
    1.30
    мо
    1.25
     Moha
    1.24
    Activations Density 0.245%

    No Known Activations