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. 5-GEMMASCOPE-RES-16K
    6. 7081
    Prev
    Next
    INDEX
    Explanations

    mechanical devices or explosive objects and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.55
    >");
    
    -0.53
    Vidu
    -0.53
     Pits
    -0.52
     EnglishChoose
    -0.52
     sahiptir
    -0.52
     validamos
    -0.51
     匿名
    -0.51
    ACTED
    -0.50
     Sketches
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.55
    Rüyada
    0.53
    šech
    0.50
    EndGlobalSection
    0.48
    ностран
    0.48
    dbus
    0.47
    GEBURTSDATUM
    0.47
    gameserver
    0.47
    таратура
    0.47
    ngrx
    0.46
    Activations Density 0.601%

    No Known Activations