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. 14-GEMMASCOPE-RES-16K
    6. 10791
    Prev
    Next
    INDEX
    Explanations

    frequent mentions and discussions of the concept of "nation" and its related aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /***/
    -1.16
    createServer
    -1.04
     nahilalakip
    -1.00
    BagLayout
    -0.99
     ControllerBase
    -0.94
    IsMutable
    -0.92
    delaire
    -0.92
    upaten
    -0.87
     estekak
    -0.86
    ibatis
    -0.84
    POSITIVE LOGITS
    ally
    0.99
    ation
    0.89
     Zon
    0.89
    ension
    0.87
    Zon
    0.85
    ion
    0.84
    sion
    0.84
    motion
    0.83
    dimension
    0.83
    ning
    0.82
    Activations Density 0.207%

    No Known Activations