© 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. 27-GEMMASCOPE-RES-16K
    11. 10188
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     estekak
    -0.65
     للمعارف
    -0.64
    TagMode
    -0.61
    batore
    -0.59
     '\\;'
    -0.56
    лтемелер
    -0.55
    licon
    -0.54
    MessageOf
    -0.54
    ContentAsync
    -0.53
    IntoConstraints
    -0.53
    POSITIVE LOGITS
     fraction
    0.79
     fractions
    0.66
    fraction
    0.63
     Fraction
    0.58
    Fraction
    0.58
     Prozent
    0.57
     fractional
    0.57
     proportion
    0.55
     percent
    0.55
     percentage
    0.54
    Activations Density 1.733%

    No Known Activations