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. 8-GEMMASCOPE-RES-16K
    6. 15175
    Prev
    Next
    INDEX
    Explanations

    proper formatting indicators or layout elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excep
    -0.61
     fronte
    -0.60
     المعيارى
    -0.58
     quận
    -0.58
    atung
    -0.57
    waw
    -0.54
    anmoins
    -0.52
     σχ
    -0.50
     define
    -0.49
    eraard
    -0.49
    POSITIVE LOGITS
     GenerationType
    1.02
    )");
    
    0.94
    ValueStyle
    0.87
     propOrder
    0.86
     للاسماء
    0.81
    ")){
    
    0.79
    esModule
    0.78
    awtextra
    0.77
    protoimpl
    0.76
    __);
    0.75
    Activations Density 0.072%

    No Known Activations