© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102640
    Prev
    Next
    INDEX
    Explanations

    geographical locations and entities related to New Zealand

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

    New Zealand related locations and demographics

    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
     HasFactory
    -0.90
     FetchType
    -0.77
     <<<<<<<<<<<<<<
    -0.75
     CURIAM
    -0.74
    TypedDataSet
    -0.73
    parsedMessage
    -0.73
    httphttps
    -0.72
    Diweddarwch
    -0.71
     indisponible
    -0.71
     kasarigan
    -0.70
    POSITIVE LOGITS
     Zealand
    0.94
    
    0.88
     NZ
    0.83
     Auckland
    0.83
    NZ
    0.76
     ZEALAND
    0.73
     Maori
    0.73
    Auckland
    0.72
     Kiwi
    0.69
     zealand
    0.60
    Activations Density 0.019%

    No Known Activations