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. 14261
    Prev
    Next
    INDEX
    Explanations

    function declarations and control flow structures in programming code

    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
    org
    -0.50
    int
    -0.47
    inen
    -0.46
    ue
    -0.45
    nor
    -0.45
    nel
    -0.44
    back
    -0.44
     national
    -0.43
    ino
    -0.43
    orm
    -0.43
    POSITIVE LOGITS
     Normdatei
    0.98
    tagHelperRunner
    0.91
    GEBURTSDATUM
    0.88
    extAlignment
    0.83
    QMetaType
    0.78
    URLException
    0.78
    abestanden
    0.74
    izr
    0.74
     kiệm
    0.73
    :✨
    0.72
    Activations Density 0.055%

    No Known Activations