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

    Neuronpedia

    APICircuit 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. 2970
    Prev
    Next
    INDEX
    Explanations

    details related to aquatic environments and the maintenance of marine organisms

    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
     تضيفلها
    -0.78
    IsContent
    -0.63
    ThroughAttribute
    -0.61
    bestos
    -0.60
    BeginContext
    -0.59
     MainAxisSize
    -0.58
    ScopeManager
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    ConverterFactory
    -0.57
    ValueStyle
    -0.56
    POSITIVE LOGITS
     tank
    1.02
     aquarium
    0.93
     Tank
    0.83
    Tank
    0.82
     Aquarium
    0.79
     tanks
    0.76
    tank
    0.76
    aquarium
    0.71
    TANK
    0.71
     TANK
    0.70
    Activations Density 0.106%

    No Known Activations