© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9947
    Prev
    Next
    INDEX
    Explanations

    words associated with orthogonality or orthogonal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.60
    ("]");
    -0.59
     sya
    -0.54
    TimeUnit
    -0.52
     Wicidata
    -0.51
    PendingIntent
    -0.51
    MouseListener
    -0.50
    ABUL
    -0.49
     призна
    -0.49
     PopupWindow
    -0.48
    POSITIVE LOGITS
     orth
    0.92
     Orth
    0.90
    orth
    0.84
    Orth
    0.83
    ORTH
    0.77
     BorderSide
    0.75
    \/
    0.74
    izado
    0.74
    SpringRunner
    0.72
    InjectAttribute
    0.71
    Activations Density 0.087%

    No Known Activations