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. 21-GEMMASCOPE-RES-16K
    6. 1999
    Prev
    Next
    INDEX
    Explanations

    words related to memorial events and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suele
    -0.55
    (&:
    -0.55
    ->$
    -0.53
    <>();
    
    -0.52
    /*!
    -0.50
    ganan
    -0.50
    Parece
    -0.48
     suelen
    -0.48
    /*:
    -0.48
     =>
    
    -0.48
    POSITIVE LOGITS
     الحره
    0.73
     offici
    0.73
     interment
    0.72
     predeceased
    0.67
    XmlAccessorType
    0.66
     @"/
    0.66
    StoreMessageInfo
    0.65
     graves
    0.63
     célébr
    0.63
    Distribuzione
    0.62
    Activations Density 0.014%

    No Known Activations