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. 9-GEMMASCOPE-RES-16K
    6. 1764
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physics, especially in the context of plasmonics and particle interactions

    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
    cephala
    -0.53
    buttonBar
    -0.52
     taste
    -0.45
    <bos>
    -0.45
    ligente
    -0.44
    olera
    -0.43
    ignment
    -0.43
    zerland
    -0.42
    copg
    -0.41
    ágok
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.85
    참고
    0.63
    XmlAccessorType
    0.63
     pulmonar
    0.62
    Tracce
    0.61
    :✨
    0.59
     térm
    0.58
    ::_('
    0.58
     Bolo
    0.58
    WebServlet
    0.58
    Activations Density 1.431%

    No Known Activations