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. 21-GEMMASCOPE-RES-16K
    6. 8394
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups involved in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allAfrica
    -0.63
    TagMode
    -0.61
    setVerticalGroup
    -0.59
    Clik
    -0.57
    invokeLater
    -0.54
    ViewInit
    -0.50
    WindowListener
    -0.49
    ArgsConstructor
    -0.49
     retirement
    -0.48
     señora
    -0.47
    POSITIVE LOGITS
    verifyException
    0.65
    djangoproject
    0.60
     fidanz
    0.53
     ostavi
    0.53
    __))
    0.53
    enzie
    0.51
     latitudes
    0.51
    Enlaces
    0.51
    AndroidJUnit
    0.50
    conhe
    0.49
    Activations Density 0.102%

    No Known Activations