© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9972
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "inner" and related terms, particularly in contexts emphasizing positivity or fortuitous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sikkert
    -0.67
    ScreenState
    -0.65
     romantique
    -0.62
    TabStop
    -0.59
     Regno
    -0.59
    ciutto
    -0.58
    BagLayout
    -0.57
    phée
    -0.57
    berdayakan
    -0.56
    nello
    -0.56
    POSITIVE LOGITS
     challenged
    0.71
    好在
    0.65
     Inner
    0.64
     Fortunately
    0.63
     bris
    0.61
    datab
    0.60
    الصفحه
    0.59
     suing
    0.58
    Fortunately
    0.58
    DataRow
    0.57
    Activations Density 0.074%

    No Known Activations