© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs, especially those associated with case statements and variable declarations

    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
    adaptiveStyles
    -0.90
     HttpNotFound
    -0.87
     Paglinawan
    -0.86
     NDEBUG
    -0.84
     становника
    -0.82
     فريبيس
    -0.80
    bewerken
    -0.79
    AsUp
    -0.77
     ControllerBase
    -0.77
     otomatig
    -0.77
    POSITIVE LOGITS
     مشين
    0.54
    imed
    0.54
    帖最后由
    0.50
    mtable
    0.49
     Like
    0.48
    aring
    0.48
     mit
    0.47
    hogy
    0.45
    mita
    0.44
    tep
    0.44
    Activations Density 0.160%

    No Known Activations