© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6231
    Prev
    Next
    INDEX
    Explanations

    strings used in user interface elements

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

    Followed by "name" within XML string resources

    np_acts-logits-general · gemini-2.0-flash

    string name or component id

    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
     Normdatei
    -0.58
    localVar
    -0.58
     Italijani
    -0.58
    quelize
    -0.57
     ''
    -0.53
     LUMP
    -0.53
    ::_('
    -0.52
     Италијани
    -0.49
     وتسجيلات
    -0.49
     ""
    -0.48
    POSITIVE LOGITS
    >
    0.79
     Baillargeon
    0.65
    migrationBuilder
    0.61
    μως
    0.61
    ></
    0.59
     class
    0.55
     cref
    0.54
    makeConstraints
    0.53
     key
    0.53
    延伸閱讀
    0.53
    Activations Density 0.370%

    No Known Activations