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. 6-GEMMASCOPE-RES-16K
    6. 13629
    Prev
    Next
    INDEX
    Explanations

    phrases related to removing or getting rid of something, particularly in a legal or medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.75
    脚注の使い方
    -0.75
    esgue
    -0.72
    новништво
    -0.72
    তথ্যসূত্র
    -0.72
    AutoScale
    -0.69
    Демографія
    -0.67
    
    -0.66
    órmula
    -0.66
     Wikimedijinoj
    -0.66
    POSITIVE LOGITS
     possession
    0.88
    手に入
    0.68
     Possession
    0.64
     bezit
    0.61
    possession
    0.61
     acquire
    0.60
     custody
    0.59
     rid
    0.59
     dispose
    0.57
     acquiring
    0.56
    Activations Density 0.256%

    No Known Activations