© 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. 16-GEMMASCOPE-RES-65K
    11. 27789
    Prev
    Next
    INDEX
    Explanations

    references to sinks and drainage systems

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

    sink or and blink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drummond
    -0.98
    tadır
    -0.96
    SuppressLint
    -0.91
     protoimpl
    -0.87
    PhysRev
    -0.85
    XmlAccessorType
    -0.81
    CodeAttribute
    -0.80
    PhysRevD
    -0.77
    orghini
    -0.77
    RTHOOK
    -0.77
    POSITIVE LOGITS
     sink
    1.50
     Sink
    1.37
     sinks
    1.30
    Sink
    1.28
     Sinks
    1.14
    sink
    1.06
     sank
    1.06
     sunk
    1.00
     sinking
    0.84
     Rine
    0.79
    Activations Density 0.012%

    No Known Activations