© 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. 3-GEMMASCOPE-RES-16K
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    references to columns, particularly in a data or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.85
    BibitemShut
    -0.72
     دریافت‌شده
    -0.71
    interopRequire
    -0.71
    外部リンク
    -0.70
    Jereo
    -0.69
    Zeus
    -0.69
    JspWriter
    -0.69
    querade
    -0.68
    AKT
    -0.68
    POSITIVE LOGITS
     col
    2.83
     Col
    2.82
    col
    2.81
    Col
    2.80
     COL
    2.43
    COL
    2.34
     cols
    1.87
    Cols
    1.76
     COLL
    1.75
     kol
    1.68
    Activations Density 0.086%

    No Known Activations