© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5822
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to functions and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.57
    GOTREF
    -0.47
    KeySpec
    -0.47
    Hozzáférés
    -0.46
    sphase
    -0.45
    WebControls
    -0.45
    Géographie
    -0.44
    первых
    -0.44
    Referências
    -0.43
     Fields
    -0.43
    POSITIVE LOGITS
    -------------</
    0.81
    rungsseite
    0.79
    uxxxx
    0.77
     otomatig
    0.72
     occhiali
    0.71
    AnchorTagHelper
    0.70
    ISODE
    0.69
     समीक्षक
    0.68
     ujednoznacz
    0.68
    примеча
    0.67
    Activations Density 1.273%

    No Known Activations