© 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. 2-GEMMASCOPE-RES-16K
    11. 11704
    Prev
    Next
    INDEX
    Explanations

    instances of the word "attract" and its variations

    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
     للاسماء
    -0.57
     Wikimedijinoj
    -0.53
    JNIEnv
    -0.51
    omitempty
    -0.50
    IndentedString
    -0.50
     finesse
    -0.48
    HideFlags
    -0.47
    RefNanny
    -0.46
    RTCK
    -0.46
    FunctionFlags
    -0.46
    POSITIVE LOGITS
    0.79
     attraction
    0.74
     attracted
    0.72
     Attraction
    0.71
    attra
    0.61
    ordinary
    0.60
     attracting
    0.60
     attractions
    0.57
     attract
    0.57
     ordinary
    0.57
    Activations Density 0.132%

    No Known Activations