© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    various usage patterns of the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orb
    -0.51
    Демографія
    -0.50
     Савез
    -0.50
    aratus
    -0.47
    ánicas
    -0.46
     demografica
    -0.45
    Orb
    -0.45
    Autoritní
    -0.44
    osene
    -0.43
    :✨
    -0.43
    POSITIVE LOGITS
    or
    1.05
     eller
    0.86
     vagy
    0.85
     oder
    0.82
     nebo
    0.74
     alebo
    0.73
     ou
    0.73
     atau
    0.69
    oder
    0.66
    OR
    0.66
    Activations Density 0.248%

    No Known Activations