© 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. 27-GEMMASCOPE-RES-16K
    11. 12210
    Prev
    Next
    INDEX
    Explanations

    references and descriptions of flowers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endif
    -0.40
    vignon
    -0.38
    iens
    -0.37
     reinforcing
    -0.36
    iserie
    -0.36
    lippery
    -0.36
     unterstüt
    -0.36
     Ahnung
    -0.36
    ífica
    -0.36
    ństwo
    -0.35
    POSITIVE LOGITS
    Flower
    0.81
     Flower
    0.81
     FLOWER
    0.74
     Flowers
    0.71
     flower
    0.70
    Flowers
    0.69
     petals
    0.68
     kasarigan
    0.62
     petal
    0.60
     Floral
    0.59
    Activations Density 0.089%

    No Known Activations