© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    specific dates and times referenced in the document

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

    Month after a date

    np_acts-logits-general · gemini-2.0-flash

    months and dates

    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
     representation
    -0.34
     players
    -0.32
     meg
    -0.32
     jour
    -0.31
     accidental
    -0.31
    お客
    -0.31
     vere
    -0.31
     viewers
    -0.30
     seg
    -0.30
    自分も
    -0.29
    POSITIVE LOGITS
    tonode
    0.68
     snippetHide
    0.66
    GOTREF
    0.65
     October
    0.63
     autumn
    0.63
     Autumn
    0.62
     September
    0.61
    HideFlags
    0.61
    autumn
    0.59
    cember
    0.59
    Activations Density 0.212%

    No Known Activations