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. 21-GEMMASCOPE-RES-16K
    6. 7167
    Prev
    Next
    INDEX
    Explanations

    references to events and competitions in sports and athletics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चुनें
    -0.71
    tagHelperRunner
    -0.64
     consultato
    -0.63
    CodeAttribute
    -0.61
     nahilalakip
    -0.59
    GOTREF
    -0.57
    pagnes
    -0.55
    mergeFrom
    -0.52
    Routine
    -0.50
     STAND
    -0.49
    POSITIVE LOGITS
     conference
    0.86
     festival
    0.78
     championships
    0.76
     Conference
    0.70
     congress
    0.69
     congreso
    0.69
     annual
    0.67
     conférence
    0.67
     convention
    0.67
    fest
    0.66
    Activations Density 0.206%

    No Known Activations