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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8875
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and data structures, particularly in the context of APIs and JSON formatting

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

    Strings starting with "dL", "mL", "API", "dA", or "mA"

    np_acts-logits-general · gemini-2.0-flash

    API, units, and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steve
    -0.32
     ri
    -0.32
     Frank
    -0.30
    AI
    -0.30
     CA
    -0.30
    hypothesis
    -0.30
      
    -0.30
    SWIG
    -0.30
     El
    -0.29
     Jarvis
    -0.29
    POSITIVE LOGITS
     CreateTagHelper
    0.70
    ScopeManager
    0.69
    MessageOf
    0.67
     AttributeSet
    0.66
     NSCoder
    0.63
     initComponents
    0.61
     queſta
    0.60
    blurRadius
    0.60
    featureID
    0.58
     Autorizaciones
    0.58
    Activations Density 0.339%

    No Known Activations