© 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. 10387
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and disease

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

    academic publications

    np_acts-logits-general · gemini-2.0-flash

    journal citations with volumes and page numbers

    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
    WebElementEntity
    -0.76
    aarrggbb
    -0.71
    mybatisplus
    -0.69
    UseVisualStyle
    -0.67
     noDo
    -0.66
     désolés
    -0.66
    BeginContext
    -0.65
    XmlAccessType
    -0.65
     surla
    -0.64
     pinulongan
    -0.64
    POSITIVE LOGITS
    AndEndTag
    0.44
     ro
    0.42
     po
    0.40
    …………………………………………
    0.39
    एको
    0.39
    Nop
    0.38
    imai
    0.38
     Can
    0.38
     خلق
    0.37
     Wartawan
    0.36
    Activations Density 0.154%

    No Known Activations