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. 14-GEMMASCOPE-RES-16K
    6. 151
    Prev
    Next
    INDEX
    Explanations

    references to groups or classifications, particularly regarding tribal or confederate structures in historical contexts

    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
    LabelTagHelper
    -0.48
    èque
    -0.46
    oghi
    -0.46
    mobileqq
    -0.46
    view
    -0.42
    salms
    -0.42
    uarine
    -0.42
    τή
    -0.41
    Abit
    -0.40
    acamata
    -0.40
    POSITIVE LOGITS
    bootstrapcdn
    0.93
    called
    0.83
    
    0.81
     called
    0.81
     Called
    0.80
     sogenannte
    0.79
     sogenannten
    0.78
     CALLED
    0.74
     appelée
    0.74
    Called
    0.73
    Activations Density 0.315%

    No Known Activations