© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6979
    Prev
    Next
    INDEX
    Explanations

    elements related to reading and writing data in a programming context, particularly in Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIdentifier
    -0.74
     Paglinawan
    -0.72
    sidemargin
    -0.69
    ISupport
    -0.67
    DebuggerStep
    -0.66
    RegistryLite
    -0.65
    Spoljašnje
    -0.63
    encodeWith
    -0.62
     (!__
    -0.62
    orghe
    -0.61
    POSITIVE LOGITS
    DriverManager
    0.64
     ролях
    0.54
     InputDecoration
    0.52
     DriverManager
    0.50
    seamnă
    0.49
     Andra
    0.48
     juniors
    0.47
     tratta
    0.46
     Athenians
    0.46
     jsPsych
    0.45
    Activations Density 0.087%

    No Known Activations