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. 24-GEMMASCOPE-RES-16K
    6. 1052
    Prev
    Next
    INDEX
    Explanations

    technical terms and equations related to quantum mechanics and superconductivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quantum physics/mechanics Hamiltonians

    np_acts-logits-general · gemini-2.0-flash

    quantum dot Hamiltonian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dry
    -0.39
     automatic
    -0.36
     campeones
    -0.35
     basah
    -0.35
     Maurer
    -0.35
     usted
    -0.35
     camiones
    -0.34
    醐
    -0.34
     hydraulic
    -0.34
     Steiner
    -0.33
    POSITIVE LOGITS
     snippetHide
    0.66
    endphp
    0.66
     quantum
    0.63
    __*/
    0.62
     Italijani
    0.60
     otomatig
    0.60
    Abit
    0.60
    Aholisi
    0.59
    MLLoader
    0.57
     '\\;'
    0.56
    Activations Density 2.211%

    No Known Activations