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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4659
    Prev
    Next
    INDEX
    Explanations

    terms related to risk, particularly in medical or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebMethod
    -0.54
    انيف
    -0.50
     erſt
    -0.49
    quiti
    -0.45
    setupUi
    -0.45
    WebRequest
    -0.44
    ActionMode
    -0.44
    TypedDataSet
    -0.44
    Uninitialized
    -0.43
    IntoConstraints
    -0.43
    POSITIVE LOGITS
    tagHelper
    0.60
    Enllaces
    0.52
     wander
    0.52
     anonymous
    0.47
     Anonymous
    0.46
     Conscious
    0.46
    isNameExpr
    0.45
     wandered
    0.45
     conscious
    0.44
     wandering
    0.44
    Activations Density 1.392%

    No Known Activations