© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 7
    Prev
    Next
    INDEX
    Explanations

    references to metadata in technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to metadata management concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    metadataMEMORANDUM OPINION

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnableWeb
    -0.76
    fromCharCode
    -0.72
    o
    -0.66
    WebServlet
    -0.65
     Giles
    -0.60
     désolés
    -0.59
    رحلة
    -0.59
    ীর
    -0.59
    cohort
    -0.58
    iglio
    -0.58
    POSITIVE LOGITS
     Metadata
    0.71
     metadata
    0.65
    IVEREF
    0.64
    metadata
    0.61
    TagMode
    0.56
     незавершена
    0.56
     Inflate
    0.56
    erequisite
    0.56
    Geplaatst
    0.55
    Metadata
    0.54
    Activations Density 0.009%

    No Known Activations