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. 17-GEMMASCOPE-RES-16K
    6. 13339
    Prev
    Next
    INDEX
    Explanations

    references to genetic factors and biological pathways related to mitochondrial function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.79
    JspWriter
    -0.78
     թվական
    -0.77
     <>",
    -0.74
    hasMoreElements
    -0.73
    Gön
    -0.72
     INTERESAR
    -0.69
    ViewInit
    -0.69
    addContainerGap
    -0.66
     bezeichneter
    -0.65
    POSITIVE LOGITS
     الرياضيه
    0.59
    XmlAccessType
    0.56
     Persia
    0.43
     tæt
    0.43
    RenderAtEndOf
    0.42
    ẫ
    0.42
     hjälp
    0.41
     leur
    0.39
    šče
    0.39
     niečo
    0.39
    Activations Density 0.793%

    No Known Activations