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. 12-GEMMASCOPE-RES-16K
    6. 2906
    Prev
    Next
    INDEX
    Explanations

    components and layouts used in graphical user interface programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.58
    pinephrine
    -0.51
     Needham
    -0.49
    equalsIgnoreCase
    -0.49
    sschule
    -0.48
    rovna
    -0.47
    assertAll
    -0.47
    dou
    -0.46
     Gallen
    -0.46
     behaviour
    -0.45
    POSITIVE LOGITS
     initComponents
    1.29
     StatelessWidget
    1.03
    awtextra
    0.93
    ">//
    0.86
     Roskov
    0.78
    setViewportView
    0.76
     StatefulWidget
    0.71
     JTextField
    0.70
    DockStyle
    0.68
     createState
    0.66
    Activations Density 0.013%

    No Known Activations