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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7325
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to openings and seals in mechanical or electronic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     dezelve
    -0.52
     zijne
    -0.51
     regalías
    -0.48
     tecnológicos
    -0.46
     comerciais
    -0.45
     desierto
    -0.45
     pérd
    -0.45
    QMetaType
    -0.45
     contemporain
    -0.44
     témoin
    -0.44
    POSITIVE LOGITS
     hole
    0.77
     holes
    0.76
     Hole
    0.72
     Holes
    0.71
    hole
    0.69
     openings
    0.68
     opening
    0.68
    holes
    0.66
     window
    0.64
    Hole
    0.63
    Activations Density 0.708%

    No Known Activations