© 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. 28-GEMMASCOPE-RES-16K
    11. 9948
    Prev
    Next
    INDEX
    Explanations

    references to recent news or events, particularly those involving details and timelines

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

    Date and size information

    np_acts-logits-general · gemini-2.0-flash

    timestamps and file sizes

    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
    ➯
    -0.57
     kasarigan
    -0.52
    хьтан
    -0.51
    -------------</
    -0.51
    うら
    -0.49
     Meksiku
    -0.48
     userid
    -0.47
     Exacts
    -0.47
    roleId
    -0.46
    請繼續往下閱讀
    -0.46
    POSITIVE LOGITS
     propOrder
    0.54
     defaultstate
    0.38
     vänt
    0.38
    ModelSerializer
    0.37
    GOTREF
    0.36
     règne
    0.36
    exitRule
    0.36
     közé
    0.35
     vectorielles
    0.35
     ·
    0.34
    Activations Density 0.908%

    No Known Activations