© 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. 10739
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and operations in a software context

    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
    ↵↵
    -2.56
    ↵↵↵
    -1.13
    ↵↵↵↵
    -1.07
    ↵↵↵↵↵
    -0.89
    ↵↵↵↵↵↵
    -0.85
    ↵↵↵↵↵↵↵
    -0.82
    ↵↵↵↵↵↵↵↵
    -0.80
    ↵↵↵↵↵↵↵↵↵
    -0.71
    ↵↵↵↵↵↵↵↵↵↵
    -0.68
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.68
    POSITIVE LOGITS
     EnglishChoose
    0.89
    出版年
    0.81
    AndEndTag
    0.80
    webElementXpaths
    0.74
    OGND
    0.73
    IntoConstraints
    0.71
    MemoryWarning
    0.71
     незавершена
    0.70
    DeleteBehavior
    0.66
    WebElementEntity
    0.64
    Activations Density 1.456%

    No Known Activations