© 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. 0-GEMMASCOPE-RES-16K
    11. 8233
    Prev
    Next
    INDEX
    Explanations

    instances of the word "relate" and its variations, indicating a focus on relationships or connections between concepts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.71
     MainAxisSize
    -0.68
    parsedMessage
    -0.66
    MethodManager
    -0.64
    respectively
    -0.62
    IntoConstraints
    -0.62
    ftagPool
    -0.61
     للاسماء
    -0.60
    MLLoader
    -0.58
    fjspx
    -0.57
    POSITIVE LOGITS
     Rel
    1.87
    Rel
    1.73
     REL
    1.55
     relate
    1.48
    REL
    1.35
     relates
    1.33
     rel
    1.30
    relate
    1.29
    rel
    1.29
     rela
    1.23
    Activations Density 0.192%

    No Known Activations