© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 984
    Prev
    Next
    INDEX
    Explanations

    references to improvements and enhancements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.60
    ArrowToggle
    -0.54
    KURZBESCHREIBUNG
    -0.50
    AnchorStyles
    -0.47
     VIAF
    -0.47
    makeText
    -0.47
     hochzeit
    -0.47
    successfully
    -0.45
    請繼續往下閱讀
    -0.45
     successfully
    -0.44
    POSITIVE LOGITS
     suited
    0.98
    suited
    0.82
     equipped
    0.77
     behaved
    0.66
    equipped
    0.65
     positioned
    0.58
     understood
    0.58
     geeignet
    0.57
     organized
    0.56
     quality
    0.55
    Activations Density 0.158%

    No Known Activations