© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1918
    Prev
    Next
    INDEX
    Explanations

    references to medical mechanisms and treatments

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

    need or needs

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    DockStyle
    -0.89
     للمعارف
    -0.61
     ujednoznacz
    -0.61
    textTheme
    -0.60
    ButterKnife
    -0.58
    NOSIS
    -0.58
    CodedInputStream
    -0.56
    جغرافيا
    -0.54
     LCCN
    -0.53
     Infórmanos
    -0.53
    POSITIVE LOGITS
     need
    2.11
     needs
    2.01
     Needs
    1.96
     Need
    1.88
    needs
    1.85
    Needs
    1.85
    need
    1.85
    Need
    1.80
     NEEDS
    1.60
     NEED
    1.54
    Activations Density 0.260%

    No Known Activations