© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14741
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sara" or related variations, often in a medical or health-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Résultats
    -0.40
     Bef
    -0.38
     olympiques
    -0.38
    🖨
    -0.38
    zondere
    -0.37
     Ambiental
    -0.36
     Perubahan
    -0.36
    機會
    -0.36
     Dimensiones
    -0.35
     gelassen
    -0.35
    POSITIVE LOGITS
    Sar
    0.79
     Sar
    0.79
     sar
    0.71
    MigrationBuilder
    0.61
    sar
    0.61
     SAR
    0.60
     يتيمه
    0.58
     sarco
    0.57
     Sarac
    0.56
    rungsseite
    0.54
    Activations Density 0.173%

    No Known Activations