© 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. 30-GEMMASCOPE-RES-16K
    11. 13288
    Prev
    Next
    INDEX
    Explanations

    elements associated with author contributions and acknowledgments in research papers

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

    Abbreviations of researchers' initials

    np_acts-logits-general · gemini-2.0-flash

    author initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detail
    -0.34
     diploma
    -0.33
     fermés
    -0.32
     armat
    -0.31
     už
    -0.31
     geni
    -0.30
     already
    -0.30
    extAlignment
    -0.30
     Already
    -0.29
    testens
    -0.29
    POSITIVE LOGITS
     JB
    0.80
     JM
    0.79
     JL
    0.75
     JW
    0.73
    JM
    0.72
    JB
    0.72
     JC
    0.71
    JL
    0.71
     JS
    0.70
     typelib
    0.70
    Activations Density 0.486%

    No Known Activations