© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2599
    Prev
    Next
    INDEX
    Explanations

    references to parameter values and structures in a coding or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.61
    tagHelperRunner
    -0.54
    RegressionTest
    -0.49
     africains
    -0.40
     geração
    -0.38
     competición
    -0.37
     promesas
    -0.37
    BeginContext
    -0.37
     cờ
    -0.36
     APPELLANT
    -0.35
    POSITIVE LOGITS
     quantities
    0.66
     الرياضيه
    0.65
     purchase
    0.62
     ItemStack
    0.62
     purchases
    0.60
     qty
    0.60
    CartItem
    0.59
     quantity
    0.59
     items
    0.59
     Items
    0.58
    Activations Density 0.273%

    No Known Activations