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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 2557
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data privacy and security practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -1.18
     nakalista
    -1.03
    jspx
    -1.02
    MemoryWarning
    -0.97
    تقاوى
    -0.88
    principalColumn
    -0.83
     pinulongan
    -0.81
    WebServlet
    -0.79
     noqa
    -0.78
    jsxFileName
    -0.77
    POSITIVE LOGITS
     betweenstory
    0.77
     utafitiHapana
    0.56
    windowFixed
    0.53
     maît
    0.50
     sitten
    0.47
    ArrowToggle
    0.47
    titleMargin
    0.46
    qvarna
    0.43
    yttö
    0.43
    casco
    0.43
    Activations Density 0.327%

    No Known Activations