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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1054
    Prev
    Next
    INDEX
    Explanations

    references to specific materials and elements related to construction or structural engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.50
    Personensuche
    -0.45
    Plural
    -0.43
     aislado
    -0.42
     mecánico
    -0.42
     oração
    -0.42
     aikana
    -0.41
     bolsillo
    -0.40
    diyah
    -0.40
    Liga
    -0.40
    POSITIVE LOGITS
     Blood
    0.98
     Water
    0.96
     Steel
    0.95
     Glass
    0.94
     Iron
    0.93
     Wood
    0.91
     Stone
    0.90
     Fish
    0.90
     Sugar
    0.88
     Wind
    0.85
    Activations Density 0.629%

    No Known Activations