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. 16-GEMMASCOPE-RES-16K
    6. 13109
    Prev
    Next
    INDEX
    Explanations

    references to government, politics, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arki
    -0.56
     correspondant
    -0.48
     alent
    -0.47
    valueOf
    -0.47
     دریافت‌شده
    -0.44
     connexes
    -0.44
    nia
    -0.44
     bulundu
    -0.44
     avenge
    -0.44
    ComponentScan
    -0.43
    POSITIVE LOGITS
    twimg
    0.78
     дописавши
    0.69
    artige
    0.69
    addCriterion
    0.67
    SharedCtor
    0.67
     مشين
    0.66
    AnchorStyles
    0.64
    TypedDataSet
    0.63
     snippetHide
    0.63
    RectangleBorder
    0.62
    Activations Density 0.492%

    No Known Activations