© 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. 2221
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation metrics and analytical depth

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

    [Concept] of [something]

    np_acts-logits-general · gemini-2.0-flash

    degree or quality followed by of

    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
     виправивши
    -1.01
     ویکی‌پدیای
    -0.82
     تضيفلها
    -0.81
    InSection
    -0.79
     فريبيس
    -0.79
    __*/
    -0.76
     bezeichneter
    -0.74
    GEBURTSDATUM
    -0.73
    GeoNames
    -0.73
    principalTable
    -0.72
    POSITIVE LOGITS
     nature
    0.83
     of
    0.75
    nature
    0.65
     NATURE
    0.61
    ness
    0.60
     magnitude
    0.60
    teness
    0.54
     quality
    0.54
     natureza
    0.52
     ervan
    0.51
    Activations Density 0.439%

    No Known Activations