© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1371
    Prev
    Next
    INDEX
    Explanations

    references to Australian people and places

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

    Australia or Australian

    np_acts-logits-general · gemini-2.0-flash

    Australia and Australians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    typeorm
    -0.59
    DebuggerNonUser
    -0.49
     flavorful
    -0.49
    favorite
    -0.48
    FAVOR
    -0.47
    Enrollment
    -0.47
    ThroughAttribute
    -0.47
     favorite
    -0.46
    QMetaType
    -0.45
     neighboring
    -0.45
    POSITIVE LOGITS
     Australian
    1.20
     Australia
    1.16
     Queensland
    1.12
    Australian
    1.11
    Australia
    1.11
     Australien
    1.09
     Melbourne
    1.08
     Brisbane
    1.06
     AUSTRALIA
    1.05
     Australians
    1.05
    Activations Density 0.248%

    No Known Activations