© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13800
    Prev
    Next
    INDEX
    Explanations

    graphic or programming-related terms, specifically those related to file extensions and suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.90
     للمعارف
    -0.83
     useCallback
    -0.81
    BeginContext
    -0.81
    httphttps
    -0.80
     newOwner
    -0.79
    MemoryWarning
    -0.77
    AxisAlignment
    -0.77
    RectangleBorder
    -0.76
    }`).
    -0.74
    POSITIVE LOGITS
     suffix
    0.71
    suffix
    0.66
    Suffix
    0.60
     appended
    0.55
     suffixes
    0.50
    ffix
    0.46
    SUFFIX
    0.44
    artifactId
    0.44
    缀
    0.42
     derechos
    0.42
    Activations Density 0.274%

    No Known Activations