© 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. 17-GEMMASCOPE-RES-16K
    11. 656
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and their associated subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     belonged
    -0.53
     принадлежа
    -0.52
    owned
    -0.50
     Kese
    -0.50
     belonging
    -0.49
    unci
    -0.48
     textStatus
    -0.47
     loved
    -0.47
    NSY
    -0.46
     belong
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.93
    ScopeManager
    0.81
    WithIOException
    0.77
     فريبيس
    0.74
     ujednoznacz
    0.71
    出版年
    0.70
    évaluateur
    0.70
     ویکی‌پدیای
    0.69
    曖昧さ回避
    0.68
    tagHelperRunner
    0.67
    Activations Density 0.273%

    No Known Activations