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. 15-GEMMASCOPE-RES-16K
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to coding, variables, and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.73
     InputDecoration
    -0.69
    DeleteBehavior
    -0.66
    tonsoft
    -0.63
     BoxDecoration
    -0.62
    UnusedPrivate
    -0.61
     Disqus
    -0.60
     '\\;'
    -0.60
    AsUp
    -0.60
     समीक्षाएं
    -0.60
    POSITIVE LOGITS
     cioè
    0.49
    ":
    
    0.45
    ':
    
    0.45
     pubblicato
    0.42
    قایناق‌لار
    0.42
    WebServlet
    0.42
     لیے
    0.41
    情况下
    0.41
     stesso
    0.40
    ายุ
    0.40
    Activations Density 0.330%

    No Known Activations