© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4881
    Prev
    Next
    INDEX
    Explanations

    references to specific films, their creators, and associated production elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     américa
    -0.73
    美国
    -0.72
     américains
    -0.72
    在美国
    -0.71
     Amerikaanse
    -0.71
     AMERICAN
    -0.69
    american
    -0.69
     Američ
    -0.69
     الأمريكي
    -0.69
     américain
    -0.68
    POSITIVE LOGITS
     European
    0.86
    European
    0.67
     Europe
    0.67
     Euro
    0.65
     euro
    0.60
     Europeans
    0.56
    欧洲
    0.56
     EU
    0.54
    Euro
    0.53
     europeo
    0.53
    Activations Density 1.443%

    No Known Activations