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. 10251
    Prev
    Next
    INDEX
    Explanations

    phrases indicating temporal or locational 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
    .",
    
    -0.62
    Према
    -0.61
    følgelig
    -0.59
     }}"></
    -0.57
    !")
    
    -0.56
     Month
    -0.55
    </tfoot>
    -0.54
     chi̍t
    -0.54
    ."));
    -0.54
    ocera
    -0.53
    POSITIVE LOGITS
     somewhere
    0.83
    somewhere
    0.68
     Somewhere
    0.68
    Somewhere
    0.67
    PyExc
    0.65
    AndroidJUnit
    0.62
     defaultstate
    0.58
     someplace
    0.57
     something
    0.54
    ServiceModel
    0.54
    Activations Density 0.306%

    No Known Activations