© 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. 21-GEMMASCOPE-RES-16K
    11. 12151
    Prev
    Next
    INDEX
    Explanations

    specific numerical values, institutional names, and formatting elements within texts

    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
     >=",
    -0.69
    WebVitals
    -0.69
    AccessorTable
    -0.65
    AnchorStyles
    -0.65
    interopRequire
    -0.64
     */
    -0.64
    üyada
    -0.63
     CreateTagHelper
    -0.62
    ();
    -0.60
     }}"></
    -0.59
    POSITIVE LOGITS
    kháu
    0.58
     the
    0.55
     bancaire
    0.47
     насељу
    0.45
     nationales
    0.43
     varandra
    0.43
     Nacionales
    0.42
    DataSetChanged
    0.40
     كومونز
    0.39
     nacionais
    0.39
    Activations Density 0.756%

    No Known Activations