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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39168
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to functions and equations

    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
    <code>
    -0.55
    --(
    -0.54
    <eos>
    -0.52
    ={`/
    -0.52
     muchacho
    -0.50
    ↵↵
    -0.50
    ("[
    -0.49
    <blockquote>
    -0.49
    []{
    -0.49
    ({"
    -0.48
    POSITIVE LOGITS
     صوتيه
    0.83
     lenker
    0.73
    ValueStyle
    0.72
     الرياضيه
    0.71
    存于互联网档案馆
    0.70
    RepeatedField
    0.70
     ]
    
    0.69
     ivelany
    0.69
     дописавши
    0.68
    StoryboardSegue
    0.68
    Activations Density 0.003%

    No Known Activations