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. 10-GEMMASCOPE-RES-16K
    6. 3132
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the act of pointing out discrepancies or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.66
    Демографія
    -0.62
    addCriterion
    -0.60
    
    -0.58
    ValueStyle
    -0.58
    inata
    -0.56
    NewGuid
    -0.55
    IMPORTED
    -0.52
    ής
    -0.50
     autorytatywna
    -0.50
    POSITIVE LOGITS
    SharedDtor
    0.62
    RegressionTest
    0.53
    etheless
    0.51
     purpoſe
    0.50
     myſelf
    0.49
     fubject
    0.48
    rentices
    0.48
     dalamnya
    0.48
    iNdEx
    0.47
     Houſe
    0.47
    Activations Density 0.370%

    No Known Activations