Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9817
    Prev
    Next
    INDEX
    Explanations

    references to web request and server interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    migrationBuilder
    -0.83
     LoggerFactory
    -0.72
    DriverManager
    -0.69
    esez
    -0.68
    Notae
    -0.64
    NewUrlParser
    -0.61
     JAXBElement
    -0.60
    preter
    -0.60
     समीक्षक
    -0.59
     חיצוניים
    -0.59
    POSITIVE LOGITS
    @@
    0.83
    -
    0.71
    :✨
    0.69
    +
    0.63
    RegistryLite
    0.55
    Subject
    0.50
    {#
    0.48
    <eos>
    0.48
     cuadrada
    0.47
     Vikipedi
    0.47
    Activations Density 0.150%

    No Known Activations