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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4362
    Prev
    Next
    INDEX
    Explanations

    references to "North" and "northern" regions or locations

    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
    
    -0.50
    iesta
    -0.46
    fxml
    -0.46
    SupportActionBar
    -0.44
    glEnd
    -0.44
     Paglinawan
    -0.43
     edição
    -0.43
    CastException
    -0.42
    DataAnnotations
    -0.42
    出版年
    -0.41
    POSITIVE LOGITS
     North
    3.14
    North
    3.03
     NORTH
    2.81
    NORTH
    2.78
     north
    2.56
     Northern
    2.55
    north
    2.47
     northern
    2.41
     Nord
    2.36
    Northern
    2.34
    Activations Density 0.164%

    No Known Activations