© 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 EvalsExportsinterp-engineNEWAPI 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. 1017
    Prev
    Next
    INDEX
    Explanations

    nested parentheses or related structures in code

    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
     StatefulWidget
    -0.78
    astify
    -0.62
    TagMode
    -0.60
    ecap
    -0.58
    كذا
    -0.57
    hbase
    -0.57
     resourceCulture
    -0.57
    UnusedPrivate
    -0.56
    iseries
    -0.56
    ⓘ
    -0.55
    POSITIVE LOGITS
    RectangleBorder
    0.69
    (((
    0.62
    *)((
    0.58
    الدراسه
    0.54
    bibinfo
    0.53
     createState
    0.51
    unately
    0.51
    Milli
    0.51
     Schiller
    0.51
     therefrom
    0.51
    Activations Density 0.336%

    No Known Activations