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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 6184
    Prev
    Next
    INDEX
    Explanations

    biological or taxonomic classifications of various species and their properties

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

    scientific taxonomy names, especially for species (like genus and species names with asterisks).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.81
    MLLoader
    -0.70
    webElementXpaths
    -0.70
    NameInMap
    -0.65
     <>",
    -0.64
    unmodifiable
    -0.61
    Aspiration
    -0.61
    jspx
    -0.60
    AndroidJUnit
    -0.58
    [:-
    -0.58
    POSITIVE LOGITS
     tasche
    0.78
     européennes
    0.78
     precisione
    0.74
     vectorielles
    0.72
     sauvages
    0.70
     alluminio
    0.68
     macchine
    0.68
     termica
    0.67
     européens
    0.67
     africains
    0.67
    Activations Density 0.189%

    No Known Activations