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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53379
    Prev
    Next
    INDEX
    Explanations

    references to identifiers, especially related to legal or official contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    # number rankings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.62
    WithIOException
    -0.58
    numerusform
    -0.56
    
    -0.55
    RectangleBorder
    -0.51
     stellte
    -0.49
     pertenecen
    -0.47
    awia
    -0.47
     clôture
    -0.47
     ComVisible
    -0.47
    POSITIVE LOGITS
     ranked
    0.68
     ranking
    0.64
    ranked
    0.60
    曖昧さ回避
    0.54
     rated
    0.54
    viewDidLoad
    0.54
     rank
    0.52
     Ranked
    0.51
     rankings
    0.51
     overall
    0.50
    Activations Density 0.180%

    No Known Activations