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. 7-GEMMASCOPE-RES-16K
    6. 6942
    Prev
    Next
    INDEX
    Explanations

    references to gaming mechanics and player interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artísticas
    -0.54
     navideña
    -0.52
     nocturna
    -0.51
     amorosa
    -0.51
     souverain
    -0.50
     masina
    -0.49
     Astrology
    -0.49
     pakan
    -0.49
     arrivato
    -0.49
     poética
    -0.49
    POSITIVE LOGITS
     Biôgrafia
    0.69
    protoimpl
    0.68
    yntaxException
    0.65
    SourceChecksum
    0.65
    EnableWeb
    0.64
     onCreateView
    0.64
    contentLoaded
    0.64
     ويكيميديا
    0.63
    TagMode
    0.60
     ujednoznacz
    0.60
    Activations Density 0.209%

    No Known Activations