© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    references to legal or medical issues and their implications

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

    followed by punctuation or "and"

    np_acts-logits-general · gemini-2.0-flash

    present time or specific nouns

    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
     durante
    -0.61
     during
    -0.59
     later
    -0.56
     během
    -0.52
     DURING
    -0.52
     während
    -0.50
     selama
    -0.50
     initially
    -0.50
     eventually
    -0.49
     lors
    -0.49
    POSITIVE LOGITS
     currently
    0.86
    currently
    0.83
     now
    0.80
     Currently
    0.77
     actuellement
    0.76
    Currently
    0.75
     atualmente
    0.73
     attualmente
    0.73
     actualmente
    0.71
     presently
    0.69
    Activations Density 0.533%

    No Known Activations