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. 15486
    Prev
    Next
    INDEX
    Explanations

    references to governmental and regulatory bodies related to health, safety, and environmental issues

    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
     للاسماء
    -0.96
    RegressionTest
    -0.92
    maketitle
    -0.86
     defaultstate
    -0.85
     CYTHON
    -0.80
     Paglinawan
    -0.79
     faſt
    -0.79
    AccessorTable
    -0.79
    withIdentifier
    -0.77
     Exactos
    -0.74
    POSITIVE LOGITS
     potuto
    0.46
     überg
    0.43
    tabBar
    0.41
     he
    0.41
     him
    0.38
    ussis
    0.38
    put
    0.37
    ấu
    0.36
    -"
    0.36
    "
    0.36
    Activations Density 1.058%

    No Known Activations