Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11536
    Prev
    Next
    INDEX
    Explanations

    specific addresses and geographic locations

    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
    migrationBuilder
    -0.52
    enumii
    -0.42
    mobileqq
    -0.41
     fieltro
    -0.39
    RectangleBorder
    -0.38
     silicona
    -0.37
     Irán
    -0.36
    })));
    -0.35
    外部連結
    -0.34
    delwed
    -0.34
    POSITIVE LOGITS
     Street
    1.97
     street
    1.87
     Avenue
    1.72
    Street
    1.71
     Road
    1.71
     STREET
    1.66
    street
    1.50
    Avenue
    1.45
     avenue
    1.45
     Drive
    1.45
    Activations Density 0.306%

    No Known Activations