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. 16-GEMMASCOPE-RES-16K
    6. 491
    Prev
    Next
    INDEX
    Explanations

    mentions of historical significance and notable records within various contexts

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

    "history" or "world" followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    largest history world record

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
    -0.69
    BASEPATH
    -0.64
    躇
    -0.62
     ujednoznacz
    -0.59
    AccessorTable
    -0.58
     ]
    
    -0.56
    []
    
    -0.55
    ыгана
    -0.55
    ">:
    -0.54
    Prefer
    -0.54
    POSITIVE LOGITS
    Geplaatst
    0.56
    Diwedd
    0.55
     concorda
    0.53
    :✨
    0.53
     commerciales
    0.52
     überhaupt
    0.51
     certainly
    0.51
    之一
    0.50
     Roskov
    0.48
     مصرى
    0.48
    Activations Density 0.207%

    No Known Activations