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-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12821
    Prev
    Next
    INDEX
    Explanations

    instances of runnable code blocks in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.52
    Tikang
    -0.51
    存于互联网档案馆
    -0.50
     Chwiliwch
    -0.50
    日閲覧
    -0.49
     magasiner
    -0.49
    queryInterface
    -0.48
     democrá
    -0.47
     MainAxisSize
    -0.47
     Bioaccumulative
    -0.46
    POSITIVE LOGITS
     StatefulWidget
    0.69
     StatelessWidget
    0.57
     &___
    0.50
    rungsseite
    0.46
    function
    0.44
    :
    0.42
    mbles
    0.41
    cshtml
    0.41
    MouseAdapter
    0.41
     Melan
    0.41
    Activations Density 0.020%

    No Known Activations