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. 24-GEMMASCOPE-RES-16K
    6. 5510
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions and healthcare facilities

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

    Geographical regions, states, or provinces

    np_acts-logits-general · gemini-2.0-flash

    geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.54
     ORGANIZATION
    -0.48
     measuring
    -0.40
    ORGANIZATION
    -0.39
    deutung
    -0.39
     Kelurahan
    -0.39
    culadora
    -0.38
     humanidade
    -0.38
     INTERNATIONAL
    -0.38
     computadoras
    -0.37
    POSITIVE LOGITS
     regions
    0.62
     coasts
    0.59
     nationwide
    0.59
     south
    0.58
     seaside
    0.57
     southern
    0.57
     statewide
    0.56
     coastal
    0.56
     locations
    0.55
    south
    0.54
    Activations Density 0.362%

    No Known Activations