© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8992
    Prev
    Next
    INDEX
    Explanations

    terms related to nonlinear dynamics and mathematical modeling in complex systems

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

    Nonlinear/inhomogeneous equations or processes

    np_acts-logits-general · gemini-2.0-flash

    nonlinear dynamic behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.71
    ьаж
    -0.69
     Roskov
    -0.64
    ImageContext
    -0.58
    AsUp
    -0.56
     nahilalakip
    -0.56
    󠀠
    -0.55
    UnusedPrivate
    -0.54
     AssemblyTitle
    -0.53
     surla
    -0.53
    POSITIVE LOGITS
     variable
    0.36
    Dés
    0.33
    不止
    0.30
     OnDestroy
    0.30
     multiple
    0.30
     less
    0.29
    lapsingToolbar
    0.29
     mucho
    0.28
    Variable
    0.28
     slutt
    0.28
    Activations Density 1.135%

    No Known Activations