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. 5-GEMMASCOPE-RES-16K
    6. 7584
    Prev
    Next
    INDEX
    Explanations

    code elements related to setting document attributes and values in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.88
    fromCharCode
    -0.87
    gameserver
    -0.84
    GEBURTS
    -0.81
    MarshalTo
    -0.81
    wapV
    -0.78
    DeleteBehavior
    -0.72
    homonymie
    -0.71
     /\.(
    -0.71
    rawDesc
    -0.71
    POSITIVE LOGITS
    ArgumentParser
    0.57
    N
    0.52
    Билгалдахарш
    0.52
    ,
    0.49
     كمان
    0.49
    V
    0.47
    こともあります
    0.47
    Others
    0.46
    none
    0.45
    n
    0.45
    Activations Density 0.043%

    No Known Activations