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. 10964
    Prev
    Next
    INDEX
    Explanations

    HTML tags and special character entities

    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
      
    -0.54
    mov
    -0.52
     DriverManager
    -0.52
    <table>
    -0.51
     −
    -0.49
    abestanden
    -0.49
        
    -0.49
    িনি
    -0.49
    “
    -0.49
    cad
    -0.48
    POSITIVE LOGITS
    fjspx
    0.96
    <&
    0.89
    {§
    0.81
    \&
    0.80
    InjectAttribute
    0.77
     \&
    0.75
    FromNib
    0.75
     Yugoslavia
    0.74
    %?
    0.74
     Reſ
    0.74
    Activations Density 0.706%

    No Known Activations