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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11602
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to experimental design and animal studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     server
    -0.33
     Blatt
    -0.30
     Blumen
    -0.29
     orgánico
    -0.29
     phong
    -0.29
    ish
    -0.28
     elements
    -0.27
     jurk
    -0.27
     huur
    -0.27
     spam
    -0.27
    POSITIVE LOGITS
    BufferException
    0.88
    WithIOException
    0.74
    farmer
    0.73
    Agro
    0.73
     agronom
    0.71
     farm
    0.71
     agricul
    0.70
     farms
    0.69
     farmer
    0.69
     Agricultural
    0.68
    Activations Density 0.562%

    No Known Activations