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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 16093
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to mathematical or programming functions

    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
    multicolumn
    -0.48
    OTHY
    -0.47
     another
    -0.47
    }{*}{
    -0.44
     päät
    -0.44
     argint
    -0.44
    colhead
    -0.44
    AMPLES
    -0.44
    geführt
    -0.44
     colspan
    -0.43
    POSITIVE LOGITS
    rungsseite
    1.24
    WithIOException
    1.06
    webElementXpaths
    0.82
     autorytatywna
    0.81
    UnsafeEnabled
    0.78
    Personensuche
    0.77
    }}
    
    0.74
    Legături
    0.74
     CURIAM
    0.74
     للمعارف
    0.73
    Activations Density 0.022%

    No Known Activations