© 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. 20-GEMMASCOPE-RES-16K
    11. 990
    Prev
    Next
    INDEX
    Explanations

    words related to programming and technical concepts, especially those involving integration and configuration

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

    ending in "-bility" or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    parts of words and their common endings

    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
    :✨
    -0.59
    TypedDataSet
    -0.59
     Abp
    -0.58
    InstanceState
    -0.58
    ✨:
    -0.55
    pendente
    -0.54
    ^(@
    -0.53
    :///
    -0.52
     pinulongan
    -0.51
    ]")]
    -0.51
    POSITIVE LOGITS
    mente
    0.60
    bles
    0.60
    ments
    0.58
    bility
    0.58
     Paglinawan
    0.56
    DoubleQuotes
    0.56
     isComment
    0.55
    fter
    0.55
    OGND
    0.52
    AddHtmlAttribute
    0.50
    Activations Density 0.096%

    No Known Activations