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. 10-GEMMASCOPE-RES-16K
    6. 13232
    Prev
    Next
    INDEX
    Explanations

    names of directors and notable figures in film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.75
     ujednoznacz
    -0.66
     Theſe
    -0.65
     disambiguazione
    -0.61
    homonymie
    -0.56
     bershka
    -0.55
     Allociné
    -0.55
     contextLoads
    -0.54
    ribusi
    -0.54
    amssymb
    -0.54
    POSITIVE LOGITS
    WireFormatLite
    0.63
    Pyx
    0.54
    :^(
    0.52
    ("/:
    0.49
     العنوان
    0.47
    роде
    0.46
    Citiți
    0.46
    <eos>
    0.45
     who
    0.45
    HasAnnotation
    0.45
    Activations Density 0.179%

    No Known Activations