© 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. 18-GEMMASCOPE-RES-16K
    11. 13448
    Prev
    Next
    INDEX
    Explanations

    import statements and annotations related to code structure in a programming context

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

    XML or HTML tags

    np_acts-logits-general · gemini-2.0-flash

    Maven dependencies and XML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stage
    -0.55
     farmer
    -0.51
    stage
    -0.48
     Stage
    -0.47
    jaran
    -0.47
     coti
    -0.46
     detik
    -0.46
    AddressBook
    -0.46
    Stage
    -0.45
     nghiệp
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    EDEFAULT
    0.79
    featureID
    0.78
    abestanden
    0.75
     '{@
    0.72
    ValueStyle
    0.72
    TagMode
    0.72
    évaluateur
    0.71
     EClass
    0.70
    tagHelperRunner
    0.67
    Activations Density 0.013%

    No Known Activations