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. 3-GEMMASCOPE-RES-16K
    6. 10935
    Prev
    Next
    INDEX
    Explanations

    occurrences of "base" and related object-oriented programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gioca
    -0.66
    TargetException
    -0.57
    ViewChild
    -0.56
    ctest
    -0.55
    ESTAMP
    -0.55
     romántica
    -0.54
     păr
    -0.53
    seamnă
    -0.53
     Phaser
    -0.51
    roupe
    -0.51
    POSITIVE LOGITS
     estekak
    0.72
     Wikimedijinoj
    0.71
     contextLoads
    0.67
    endphp
    0.66
     AssemblyVersion
    0.55
     transfieras
    0.54
    OGND
    0.54
    sterone
    0.52
    [['
    0.51
    Glej
    0.51
    Activations Density 0.233%

    No Known Activations