© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29478
    Prev
    Next
    INDEX
    Explanations

    terms related to scope, conditions, and outcomes in various contexts

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

    scope and its relation to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flink
    -0.70
    onViewCreated
    -0.67
     Meksiku
    -0.63
     ostavi
    -0.63
    fopen
    -0.63
    قایناقلار
    -0.61
    OrBuilder
    -0.60
     TextAppearance
    -0.59
    Jeografia
    -0.59
     onCreateView
    -0.58
    POSITIVE LOGITS
     للاسماء
    0.62
     considerably
    0.58
     than
    0.58
    ýš
    0.57
     dramatically
    0.53
     znacznie
    0.52
     substantially
    0.52
     drastically
    0.52
     significantly
    0.50
    ărul
    0.50
    Activations Density 0.333%

    No Known Activations