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. 11-GEMMASCOPE-RES-16K
    6. 10015
    Prev
    Next
    INDEX
    Explanations

    terms related to damping dynamics in physical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.65
    UnitTesting
    -0.63
    OGND
    -0.61
    complexContent
    -0.60
    WireFormatLite
    -0.60
     tartalomajánló
    -0.59
     resourceCulture
    -0.59
    TypedDataSet
    -0.58
     DBNull
    -0.57
    GOTREF
    -0.57
    POSITIVE LOGITS
     damping
    0.44
     dissipation
    0.41
    damping
    0.38
     slowing
    0.35
     Feinde
    0.35
     lenta
    0.34
     dissip
    0.34
     aéreo
    0.32
     dissipate
    0.32
     amortigu
    0.32
    Activations Density 1.360%

    No Known Activations