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. 3760
    Prev
    Next
    INDEX
    Explanations

    phrases related to future-oriented responsibilities and decision-making

    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
     Процитовано
    -0.55
    multirow
    -0.53
     Dostupné
    -0.49
    laştır
    -0.48
    FS
    -0.47
    ėk
    -0.47
    原始内容存档于
    -0.46
     keber
    -0.46
    llow
    -0.44
    createTextNode
    -0.44
    POSITIVE LOGITS
     autorytatywna
    1.00
    Demografie
    0.78
    Спасылкі
    0.69
    DoubleQuotes
    0.68
     للمعارف
    0.66
    ()")
    0.66
    ...")
    0.66
    TagMode
    0.65
     AssemblyVersion
    0.64
     Biôgrafia
    0.64
    Activations Density 0.674%

    No Known Activations