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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6529
    Prev
    Next
    INDEX
    Explanations

    technical features related to scheduling and time management options

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

    after HTML tags or special characters

    np_acts-logits-general · gemini-2.0-flash

    now / now then

    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
     Infórmanos
    -0.69
     propOrder
    -0.64
    ViewImports
    -0.61
     HasFactory
    -0.60
     <>",
    -0.57
    ItemBackground
    -0.55
    SourceChecksum
    -0.55
    RegistryLite
    -0.51
    ThroughAttribute
    -0.50
    uxxxx
    -0.49
    POSITIVE LOGITS
     now
    1.07
     désormais
    0.95
     теперь
    0.90
     ahora
    0.88
    now
    0.85
     artık
    0.85
     agora
    0.76
    ahora
    0.73
     instead
    0.73
     sekarang
    0.69
    Activations Density 0.680%

    No Known Activations