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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2038
    Prev
    Next
    INDEX
    Explanations

    concepts related to public health, fitness, and community well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.73
     inconvénients
    -0.64
     escuchadas
    -0.57
     invokingState
    -0.56
     prochaines
    -0.55
     }}"></
    -0.55
    dafx
    -0.55
     Fruits
    -0.54
    Fruits
    -0.53
    largest
    -0.53
    POSITIVE LOGITS
     دیکھیے
    0.77
     Paglinawan
    0.63
    
    0.62
     takimi
    0.59
     betweenstory
    0.59
     précision
    0.59
     versions
    0.59
     such
    0.58
    Bigr
    0.58
    Những
    0.57
    Activations Density 2.040%

    No Known Activations