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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 134
    Prev
    Next
    INDEX
    Explanations

    references to hospitals and related healthcare facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktır
    -0.68
     sexuales
    -0.64
     kohdetta
    -0.62
    AttributeSet
    -0.61
     bucal
    -0.60
    ❋
    -0.59
     danni
    -0.59
     saisir
    -0.57
     pinulongan
    -0.56
    yntaxException
    -0.56
    POSITIVE LOGITS
     Hospital
    0.92
     flow
    0.91
     Flow
    0.91
     hospital
    0.85
    Hospital
    0.81
     flowing
    0.75
     HOSPITAL
    0.72
     flowed
    0.72
    Flows
    0.70
     fluid
    0.69
    Activations Density 0.136%

    No Known Activations