© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1803
    Prev
    Next
    INDEX
    Explanations

    references to "site" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEADING
    -0.78
     bezeichneter
    -0.70
    SerializeField
    -0.67
    ”、“
    -0.67
    kull
    -0.64
     Iva
    -0.64
    ])):
    -0.63
     Тол
    -0.62
     Kearney
    -0.62
    //
    -0.61
    POSITIVE LOGITS
     Sites
    2.04
     Site
    2.00
     sites
    1.94
     SITE
    1.92
     site
    1.91
    SITE
    1.88
    Site
    1.83
    Sites
    1.79
     SITES
    1.78
    sites
    1.69
    Activations Density 0.049%

    No Known Activations