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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8012
    Prev
    Next
    INDEX
    Explanations

    information about award-winning individuals in the arts and sciences

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

    Awards, performances, and collaborations

    np_acts-logits-general · gemini-2.0-flash

    accolades and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -1.00
    principalTable
    -0.90
    Personensuche
    -0.79
    PhysRevD
    -0.78
     незавершена
    -0.77
    //
    -0.76
    Kanpo
    -0.76
     ويكيميديا
    -0.75
     opérateur
    -0.75
    AutoresizingMask
    -0.75
    POSITIVE LOGITS
     featured
    1.00
    Featured
    0.84
     Featured
    0.82
    featured
    0.76
     nationally
    0.72
     internationally
    0.63
     national
    0.62
     award
    0.61
     feature
    0.60
     international
    0.60
    Activations Density 0.222%

    No Known Activations