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. 20-GEMMASCOPE-RES-16K
    6. 9810
    Prev
    Next
    INDEX
    Explanations

    elements of programming functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.63
    y
    -0.58
    ')}
    -0.58
     iconFacebook
    -0.57
    ()][
    -0.55
    ()];
    -0.55
    ₂)
    -0.54
    "]]
    -0.53
     ་་
    -0.53
    ()].
    -0.52
    POSITIVE LOGITS
     propOrder
    0.81
     تضيفلها
    0.69
     alluminio
    0.68
     păr
    0.66
    ropods
    0.65
    szönöm
    0.65
     âgées
    0.64
    makeConstraints
    0.63
    initComponents
    0.62
    PyExc
    0.62
    Activations Density 2.096%

    No Known Activations