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. 7-GEMMASCOPE-RES-16K
    6. 14727
    Prev
    Next
    INDEX
    Explanations

    references to length scale and its relationship to system size in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prů
    -0.46
    pt
    -0.41
    kont
    -0.41
     ľud
    -0.41
    bry
    -0.40
    proba
    -0.40
    elyk
    -0.40
     keres
    -0.39
    ogli
    -0.39
    Upload
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.90
    цездатний
    0.81
    ConstraintMaker
    0.78
     Мексичка
    0.74
    =$?
    0.74
     MainAxisSize
    0.72
     Monfieur
    0.69
    الدراسه
    0.69
     jScrollPane
    0.69
     Italijani
    0.69
    Activations Density 1.156%

    No Known Activations