© 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. 12898
    Prev
    Next
    INDEX
    Explanations

    words related to floating or buoyancy

    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
     cherchés
    -0.48
     Rind
    -0.40
     Garda
    -0.40
    takers
    -0.40
     Arizona
    -0.39
     재
    -0.39
    nalité
    -0.39
     QtWidgets
    -0.38
    Arizona
    -0.38
    σιμο
    -0.38
    POSITIVE LOGITS
     Flo
    1.87
    Flo
    1.86
    flo
    1.77
     flo
    1.75
     FLO
    1.66
    FLO
    1.60
     floats
    1.55
     float
    1.50
     floating
    1.45
     FLOAT
    1.40
    Activations Density 0.317%

    No Known Activations