Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39390
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and complexity in decision-making situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.85
    __":
    
    -0.72
     betweenstory
    -0.68
    BufferException
    -0.66
    IsPostBack
    -0.60
    __':
    
    -0.60
    contentLoaded
    -0.60
    /*
    -0.60
     nemlig
    -0.60
     nämlich
    -0.59
    POSITIVE LOGITS
     оригіналу
    0.56
     compromises
    0.56
     maybe
    0.55
    interopRequire
    0.54
     perhaps
    0.52
    WEBPACK
    0.50
     misschien
    0.49
     yet
    0.48
     though
    0.48
     dilemma
    0.48
    Activations Density 0.148%

    No Known Activations