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. 3-GEMMASCOPE-RES-16K
    6. 6381
    Prev
    Next
    INDEX
    Explanations

    terms related to health surveillance and prevention measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.75
     مشين
    -0.74
     bianchi
    -0.74
     bege
    -0.72
     équi
    -0.69
    msup
    -0.68
     lourdes
    -0.66
     gial
    -0.66
     dévelo
    -0.65
     ripar
    -0.63
    POSITIVE LOGITS
     là
    2.24
    là
    1.61
     Là
    1.59
    Là
    1.39
    ilà
    0.86
    resaid
    0.76
    gdx
    0.74
     GenerationType
    0.65
    adalah
    0.64
     kuhusu
    0.64
    Activations Density 0.047%

    No Known Activations