© 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. 33-GEMMASCOPE-RES-16K
    11. 11911
    Prev
    Next
    INDEX
    Explanations

    words related to bacteria, pathogens, and immune responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.88
    AccessorTable
    -0.84
    MLLoader
    -0.80
    GEBURTSDATUM
    -0.79
    styleType
    -0.76
    RenderAtEndOf
    -0.76
     виправивши
    -0.69
    Personendaten
    -0.67
    رشف
    -0.65
    oredCriteria
    -0.64
    POSITIVE LOGITS
     evaluation
    0.60
     promotion
    0.59
     selection
    0.56
     registration
    0.56
     preparation
    0.56
     identification
    0.55
     exploration
    0.54
     exploitation
    0.54
     delivery
    0.54
     creation
    0.53
    Activations Density 1.743%

    No Known Activations