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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8390
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mario" and related characters or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mario Brothers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.48
     externi
    -0.45
     Numerade
    -0.40
     sija
    -0.39
     goede
    -0.39
     iyon
    -0.39
     nõ
    -0.38
     razonable
    -0.38
     quedado
    -0.37
    closePath
    -0.37
    POSITIVE LOGITS
     Mario
    1.18
     mario
    1.10
    Mario
    1.09
    mario
    0.98
     Nintendo
    0.71
     Bowser
    0.70
    Nintendo
    0.69
     nintendo
    0.65
     Luigi
    0.63
    nintendo
    0.61
    Activations Density 0.003%

    No Known Activations