© 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 - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    structured code elements, particularly closing brackets and syntax terminators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stylers
    -0.52
    akter
    -0.47
     stemming
    -0.46
    migrationBuilder
    -0.46
    烯
    -0.44
    HttpFoundation
    -0.44
    XmlEnum
    -0.43
    гно
    -0.43
    agoza
    -0.42
    ברס
    -0.42
    POSITIVE LOGITS
    HasAnnotation
    0.77
     lenker
    0.73
    (!__
    0.71
    BeginContext
    0.70
     الاطلاع
    0.68
    endregion
    0.68
     تضيفلها
    0.68
    ArgsConstructor
    0.68
    +#+#
    0.66
    viewDidLoad
    0.65
    Activations Density 0.203%

    No Known Activations