© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5929
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles, particularly those related to legal cases or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.78
    writeFieldEnd
    -0.65
    GEBURTSDATUM
    -0.63
    fillType
    -0.62
     Autorizaciones
    -0.59
    Tembelea
    -0.59
     NSCoder
    -0.58
     للاسماء
    -0.57
    ValueStyle
    -0.56
    ніципалі
    -0.56
    POSITIVE LOGITS
     Mc
    0.72
    Mc
    0.69
     nom
    0.57
     McC
    0.54
     McCon
    0.53
     McCar
    0.51
     pants
    0.50
     Nom
    0.50
    nom
    0.49
     McF
    0.49
    Activations Density 1.315%

    No Known Activations