© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 537
    Prev
    Next
    INDEX
    Explanations

    terms related to social and political structures involving regulation and lifting of restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postmedia
    -0.57
     SEDS
    -0.55
    dymyr
    -0.52
    ponses
    -0.52
     derselbe
    -0.52
    styleType
    -0.51
    GEBURTSDATUM
    -0.51
    Hozzáférés
    -0.50
    存于互联网档案馆
    -0.50
     ControllerBase
    -0.48
    POSITIVE LOGITS
     dependence
    0.88
     khỏi
    0.84
     reliance
    0.82
     dependency
    0.76
     initComponents
    0.72
     barriers
    0.71
     unnecessary
    0.71
    dependence
    0.69
     superfluous
    0.66
     excess
    0.65
    Activations Density 0.601%

    No Known Activations