© 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. 10022
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements

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

    Programming code or structured data

    np_acts-logits-general · gemini-2.0-flash

    Carlo models

    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
     EconPapers
    -0.53
    CrossRef
    -0.46
    OptionsMenu
    -0.42
    al
    -0.42
    ReusableCell
    -0.40
    ant
    -0.40
    тал
    -0.39
    #
    -0.39
     byl
    -0.39
    w
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.88
    tagHelperRunner
    0.83
    MessageOf
    0.80
     Cambo
    0.71
    Notae
    0.69
    dresser
    0.68
     magasiner
    0.68
    oleum
    0.67
    featureID
    0.66
     bershka
    0.66
    Activations Density 0.040%

    No Known Activations