© 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. 28-GEMMASCOPE-RES-16K
    11. 7908
    Prev
    Next
    INDEX
    Explanations

    references to individuality or personalized experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "individual" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    individual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.75
     propOrder
    -0.72
    GEBURTSDATUM
    -0.60
    WebElementEntity
    -0.55
    ⓧ
    -0.53
    ambién
    -0.52
     useAppContext
    -0.51
    Kjelder
    -0.51
     pinulongan
    -0.51
    kháu
    -0.51
    POSITIVE LOGITS
     Individual
    0.90
    Individual
    0.86
     individual
    0.82
     individ
    0.78
    individual
    0.76
    Individ
    0.75
     Individ
    0.73
     INDIVIDUAL
    0.71
    individ
    0.70
    IVIDUAL
    0.69
    Activations Density 0.070%

    No Known Activations