Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 5114
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.20
     Италијани
    -1.08
    ArrowToggle
    -0.94
     otomatig
    -0.80
    RegressionTest
    -0.77
    expandindo
    -0.77
    хьтан
    -0.76
    ьаж
    -0.75
    aarrggbb
    -0.74
     Roskov
    -0.74
    POSITIVE LOGITS
    \{\\
    0.81
     BoxDecoration
    0.73
    __(/*!
    0.67
     تضيفلها
    0.59
    prepareStatement
    0.58
     onData
    0.57
    $}}
    0.57
    LECTIONS
    0.56
    uests
    0.55
    NOPQRST
    0.55
    Activations Density 23.294%

    No Known Activations