© 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. 15-GEMMASCOPE-RES-16K
    11. 3390
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to processes and methodologies in scientific and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.59
    WireFormatLite
    -0.55
     mergeFrom
    -0.53
    UniformLocation
    -0.53
    ColumnHeaders
    -0.51
    MemoryWarning
    -0.51
    ValueStyle
    -0.51
     autorytatywna
    -0.50
     Италијани
    -0.47
    ito
    -0.46
    POSITIVE LOGITS
     advantages
    1.02
     preferred
    0.98
     Advantages
    0.97
    Advantages
    0.95
    preferred
    0.95
    advantages
    0.92
     preferable
    0.89
     Preferred
    0.87
     Vorteil
    0.86
     advantageous
    0.86
    Activations Density 0.886%

    No Known Activations