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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1771
    Prev
    Next
    INDEX
    Explanations

    references to books and authors, especially in the context of citing research or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.79
    MigrationBuilder
    -0.78
    loài
    -0.66
    AccessorTable
    -0.62
    Παραπομπές
    -0.61
     nonUne
    -0.61
    पया
    -0.58
    Rujukan
    -0.56
    mergeFrom
    -0.55
     مشين
    -0.54
    POSITIVE LOGITS
    niająca
    0.60
     الحره
    0.59
    MathML
    0.54
    illées
    0.54
    ÍST
    0.53
    sentinel
    0.51
     {}),
    0.51
    Anhalt
    0.50
    thalene
    0.50
    ionados
    0.50
    Activations Density 0.365%

    No Known Activations