© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 11953
    Prev
    Next
    INDEX
    Explanations

    transitional phrases indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.68
    ThroughAttribute
    -0.64
    ReusableCell
    -0.60
     esternos
    -0.58
     Taktlose
    -0.56
     pleaſure
    -0.54
     noemen
    -0.54
    Tembelea
    -0.51
    Buildable
    -0.50
     فريبيس
    -0.50
    POSITIVE LOGITS
     However
    0.87
     Furthermore
    0.74
     These
    0.65
     Moreover
    0.63
     Thus
    0.62
     This
    0.62
    Furthermore
    0.60
    However
    0.58
     Therefore
    0.54
     Hence
    0.54
    Activations Density 0.202%

    No Known Activations