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. 15-GEMMASCOPE-RES-16K
    6. 2723
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to leadership and command roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جع
    -0.58
    illoma
    -0.50
    Werk
    -0.49
    ronom
    -0.49
    μο
    -0.49
     pute
    -0.48
    Actu
    -0.48
     Konk
    -0.46
    kegaard
    -0.45
     Vidya
    -0.45
    POSITIVE LOGITS
    CodedInputStream
    0.86
    InSection
    0.82
     خارجية
    0.71
    RegistryLite
    0.70
     parseFrom
    0.66
    锈钢
    0.65
     onCancelled
    0.62
    contentLoaded
    0.59
    BeginInit
    0.58
     المعيارى
    0.57
    Activations Density 0.335%

    No Known Activations