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. 5-GEMMASCOPE-RES-16K
    6. 2796
    Prev
    Next
    INDEX
    Explanations

    terms related to prescriptions and medication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.81
    endregion
    -0.74
     Seidel
    -0.71
    mmation
    -0.71
     Selig
    -0.69
     sevi
    -0.69
     beschik
    -0.68
     tapa
    -0.68
     Sevilla
    -0.67
    vezető
    -0.67
    POSITIVE LOGITS
     pres
    1.08
    pres
    1.07
     Ones
    1.05
     ones
    1.01
    Ones
    0.93
     Pres
    0.86
    Pres
    0.83
     PRES
    0.83
     Coz
    0.77
     Chwiliwch
    0.75
    Activations Density 0.113%

    No Known Activations