© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4574
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "alive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brancas
    -0.49
     corrupción
    -0.49
     useStyles
    -0.46
     chrétien
    -0.45
    äldrar
    -0.42
     académica
    -0.41
     buruk
    -0.41
     nôtre
    -0.41
     orçamento
    -0.41
     procès
    -0.41
    POSITIVE LOGITS
     quanti
    0.66
     alive
    0.65
    tagHelper
    0.61
    ida
    0.55
     Quanti
    0.54
    IsMutable
    0.54
     disambiguazione
    0.54
    onAttach
    0.54
    WEBPACK
    0.54
    dest
    0.52
    Activations Density 0.662%

    No Known Activations