© 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. 20-GEMMASCOPE-RES-16K
    11. 6153
    Prev
    Next
    INDEX
    Explanations

    markup elements or tags used in a coding context

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

    HTML tags

    np_acts-logits-general · gemini-2.0-flash

    code and multilingual text

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     EClass
    -0.73
    DockStyle
    -0.72
    QMetaType
    -0.71
    WebMethod
    -0.65
    UnusedPrivate
    -0.64
    HttpPut
    -0.59
    HomeAsUpEnabled
    -0.59
     resourceCulture
    -0.58
     HttpStatusCode
    -0.54
    okości
    -0.53
    POSITIVE LOGITS
    translation
    0.74
     الحره
    0.69
    old
    0.62
     translation
    0.59
     transfieras
    0.56
     pinulongan
    0.52
    ன்ன
    0.51
     anlam
    0.50
     vieux
    0.50
     Traduction
    0.50
    Activations Density 0.035%

    No Known Activations