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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14925
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.13
     Paglinawan
    -1.07
     itſelf
    -1.02
    OGND
    -0.98
     myſelf
    -0.97
     Monfieur
    -0.96
     purpoſe
    -0.96
     <>",
    -0.94
     ſeveral
    -0.86
     Efq
    -0.85
    POSITIVE LOGITS
    .
    1.01
    ↵
    0.74
     of
    0.74
    ↵↵
    0.72
    <eos>
    0.68
    </strong>
    0.63
    ↵↵↵
    0.63
     to
    0.62
    Показать
    0.61
      
    0.61
    Activations Density 0.697%

    No Known Activations