© 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. 18-GEMMASCOPE-RES-16K
    11. 263
    Prev
    Next
    INDEX
    Explanations

    closing brackets and semicolons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     المعيارى
    -0.64
    parsedMessage
    -0.57
    nthetic
    -0.51
    Autoritní
    -0.51
    principalColumn
    -0.50
    webElementXpaths
    -0.50
    iddhar
    -0.50
    Parcelable
    -0.50
    NOPQRST
    -0.49
    offsetof
    -0.48
    POSITIVE LOGITS
    الحياه
    0.71
    ContentAsync
    0.69
     архивлан
    0.53
     sputnik
    0.52
    bufio
    0.52
    matchCondition
    0.51
     propOrder
    0.51
    égi
    0.51
    jsxFileName
    0.50
     Archiproducts
    0.50
    Activations Density 0.013%

    No Known Activations