© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6080
    Prev
    Next
    INDEX
    Explanations

    instances of authority or governance in relation to laws and public order

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.42
    altri
    -0.38
    ObservableList
    -0.33
    istream
    -0.33
    baomidou
    -0.33
     men
    -0.32
     feed
    -0.32
     ft
    -0.32
    Granada
    -0.31
     زد
    -0.31
    POSITIVE LOGITS
    󠁢
    0.74
     neighbouring
    0.61
     South
    0.59
    település
    0.58
     neighboring
    0.58
     southeastern
    0.57
     ffilmiau
    0.56
    HomeAsUpEnabled
    0.56
     Drapeau
    0.55
    ंदीखरीदारी
    0.54
    Activations Density 0.752%

    No Known Activations