© 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. 12260
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to molecular structures and comparisons between them

    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
     >=",
    -0.41
     للمعارف
    -0.37
    kegaard
    -0.36
     insuffisamment
    -0.34
     nonUne
    -0.34
    ミナル
    -0.32
    atórios
    -0.32
     AssemblyCulture
    -0.32
    bootstrapcdn
    -0.32
     afspraak
    -0.32
    POSITIVE LOGITS
     Variante
    0.81
     version
    0.80
     alternate
    0.78
    Variante
    0.74
     alternative
    0.73
     Version
    0.72
    Вариант
    0.72
     alternativo
    0.71
    Alternate
    0.69
     versione
    0.69
    Activations Density 1.434%

    No Known Activations