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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 5556
    Prev
    Next
    INDEX
    Explanations

    references to drugs and drug education initiatives

    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
    RegressionTest
    -0.78
     <<<<<<<<<<<<<<
    -0.72
     المعيارى
    -0.71
    onActivityResult
    -0.65
     насељу
    -0.64
     parseFrom
    -0.60
    IBOutlet
    -0.60
     PyTuple
    -0.59
    webElementGuid
    -0.58
     CURIAM
    -0.57
    POSITIVE LOGITS
     prevention
    0.95
     awareness
    0.92
     prévention
    0.91
    prevention
    0.83
     preven
    0.79
    preven
    0.78
     Awareness
    0.77
    Prevention
    0.77
     prevención
    0.75
     Preven
    0.74
    Activations Density 0.278%

    No Known Activations