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

    Neuronpedia

    APICircuit 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. 3-GEMMASCOPE-RES-16K
    6. 11030
    Prev
    Next
    INDEX
    Explanations

    commands related to opening and closing resources or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABULARY
    -0.58
     оригіналу
    -0.56
    /*:
    -0.54
    UpdateCommand
    -0.53
     PyLong
    -0.53
     tread
    -0.49
    MessageState
    -0.49
     MutableLiveData
    -0.49
    
    -0.49
    __["
    -0.48
    POSITIVE LOGITS
    close
    1.55
    Close
    1.25
     Close
    1.14
    CLOSE
    1.12
     CLOSE
    0.90
     onClose
    0.83
     close
    0.78
     Penh
    0.71
     关闭
    0.70
    onClose
    0.66
    Activations Density 0.057%

    No Known Activations