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. 7507
    Prev
    Next
    INDEX
    Explanations

    references to articles and authors in academic or scholarly contexts

    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
    ^(@)
    -0.76
    makeConstraints
    -0.73
     linkovi
    -0.71
    oredCriteria
    -0.70
     Autorizaciones
    -0.69
     ReSharper
    -0.66
    \"></
    -0.66
    SharedCtor
    -0.65
    %")
    -0.65
    DJANGO
    -0.64
    POSITIVE LOGITS
     ed
    1.21
     et
    0.85
     editor
    0.85
     eds
    0.84
    Ed
    0.80
     editors
    0.79
    ed
    0.79
    eds
    0.76
     Ed
    0.75
    editor
    0.73
    Activations Density 0.302%

    No Known Activations