Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5606
    Prev
    Next
    INDEX
    Explanations

    technical terms and methods related to analytical chemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.79
     ujednoznacz
    -0.72
     وتسجيلات
    -0.68
     '\\;'
    -0.67
    ConstraintMaker
    -0.65
    GEBURTSDATUM
    -0.64
    +#+
    -0.64
    Diwedd
    -0.63
    makeConstraints
    -0.63
    aughey
    -0.61
    POSITIVE LOGITS
     procedures
    0.58
     reagents
    0.54
     procedure
    0.53
     procedimentos
    0.52
     methode
    0.49
     procédure
    0.49
     assay
    0.48
     methodology
    0.48
     Anschließend
    0.47
    sima
    0.46
    Activations Density 1.359%

    No Known Activations