© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13392
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations, particularly those associated with notable institutions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gelijk
    -0.33
     داشتم
    -0.26
     anderes
    -0.25
    faccia
    -0.24
     самые
    -0.24
     okazji
    -0.23
     olivat
    -0.23
     Rücks
    -0.22
     con
    -0.22
    irut
    -0.22
    POSITIVE LOGITS
    SequentialGroup
    0.92
     Biôgrafia
    0.80
     autorytatywna
    0.78
     препратки
    0.76
    TestingModule
    0.75
    MethodManager
    0.75
     ſind
    0.74
     CURIAM
    0.73
     Италијани
    0.72
     kaarangay
    0.71
    Activations Density 0.494%

    No Known Activations