© 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. 20-GEMMASCOPE-RES-16K
    11. 7744
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purposes or goals of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.67
    
    -0.63
     ModelExpression
    -0.63
    новниш
    -0.61
    TagMode
    -0.60
    RTDA
    -0.60
    riscoll
    -0.58
     незавершена
    -0.57
    indd
    -0.57
    AnimationsModule
    -0.56
    POSITIVE LOGITS
     requires
    0.53
     Dafür
    0.42
     hierfür
    0.39
     needs
    0.38
     relies
    0.37
    GEBURTSDATUM
    0.36
     purposes
    0.36
     require
    0.36
    šanai
    0.35
     rely
    0.35
    Activations Density 0.212%

    No Known Activations