Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 902
    Prev
    Next
    INDEX
    Explanations

    terms related to casino games and slots

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

    references to casino games and related terms

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

    playtech, FireOne, exists only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    MemoryWarning
    -0.79
     nahilalakip
    -0.71
     Vikipedi
    -0.70
     الحره
    -0.68
     متعلقه
    -0.62
    İstinadlar
    -0.60
    Geplaatst
    -0.59
    DeleteBehavior
    -0.58
    NUMX
    -0.58
     useRouter
    -0.58
    POSITIVE LOGITS
    transQ
    0.66
     externs
    0.47
     ferma
    0.47
    rail
    0.45
     Chum
    0.45
    lesias
    0.44
     IRB
    0.43
     resort
    0.43
    DockStyle
    0.43
     resorts
    0.43
    Activations Density 0.024%

    No Known Activations