© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2796
    Prev
    Next
    INDEX
    Explanations

    historical political contexts and references to governance structures

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

    Sentences about Schleswig and/or Denmark

    np_acts-logits-general · gemini-2.0-flash

    political transitions and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.77
     actuellement
    -0.72
     attualmente
    -0.71
    currently
    -0.69
     Currently
    -0.67
     obecnie
    -0.67
     actualmente
    -0.66
     derzeit
    -0.65
     atualmente
    -0.63
    Currently
    -0.60
    POSITIVE LOGITS
     became
    0.67
     soon
    0.66
     began
    0.61
    ArrowToggle
    0.60
     increasingly
    0.59
     Soon
    0.59
     was
    0.59
    Soon
    0.57
    此时的
    0.57
    Eventually
    0.56
    Activations Density 1.732%

    No Known Activations