© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15830
    Prev
    Next
    INDEX
    Explanations

    references to individuals in assistant or deputy positions across various contexts

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

    "Assistant" preceding a title or position

    np_acts-logits-general · gemini-2.0-flash

    Assistant followed by role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.55
    myModal
    -0.51
    烯
    -0.50
    tituzione
    -0.48
    formData
    -0.48
    ⓘ
    -0.47
     quede
    -0.46
     egentligen
    -0.46
     dimaksud
    -0.46
    Nations
    -0.46
    POSITIVE LOGITS
    TargetException
    0.79
     pleaſure
    0.71
    MethodManager
    0.70
     IBOutlet
    0.66
    RemoteException
    0.66
    -------------</
    0.64
    twimg
    0.62
    ficulty
    0.60
    __":
    0.59
     ويكيپيديا
    0.58
    Activations Density 0.081%

    No Known Activations