© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12943
    Prev
    Next
    INDEX
    Explanations

    references to "multi" in various contexts, particularly relating to cultural, functional, and operational attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.40
     Pública
    -0.40
     Fels
    -0.35
     budowy
    -0.35
    CDCl
    -0.32
     Begründung
    -0.32
    QObject
    -0.31
    WebVitals
    -0.30
    wiście
    -0.30
     entière
    -0.29
    POSITIVE LOGITS
     Multi
    0.97
     multi
    0.89
    Multi
    0.84
     MULTI
    0.81
     MULT
    0.79
    MULTI
    0.75
    MULT
    0.69
    multi
    0.67
     myeloma
    0.66
     Multiple
    0.65
    Activations Density 0.146%

    No Known Activations