© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9838
    Prev
    Next
    INDEX
    Explanations

    details about experimental methods and results, particularly involving numerical values and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.59
    Климат
    -0.56
    Hundreds
    -0.55
    Many
    -0.53
     Many
    -0.52
     Geraadpleegd
    -0.49
     الرياضيه
    -0.48
    pagestyle
    -0.47
    iint
    -0.47
    hood
    -0.47
    POSITIVE LOGITS
    TagMode
    0.65
    setVerticalGroup
    0.65
    :^(
    0.64
    Personensuche
    0.62
     breakdown
    0.57
    SerializedSize
    0.55
     عبارت
    0.55
    routeProvider
    0.54
     összes
    0.53
     Breakdown
    0.53
    Activations Density 0.604%

    No Known Activations