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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6495
    Prev
    Next
    INDEX
    Explanations

    instances of the word "declaration" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ędziesz
    -0.69
     JpaRepository
    -0.63
    genheim
    -0.63
     withRouter
    -0.63
    Спољашње
    -0.61
     otomatig
    -0.61
    UpInside
    -0.61
    zzleHttp
    -0.60
     vermelhas
    -0.60
    Vente
    -0.58
    POSITIVE LOGITS
     declare
    1.98
     declaration
    1.92
     declared
    1.87
     declarations
    1.68
     declaring
    1.64
     declares
    1.60
     Declare
    1.57
     Declaration
    1.55
     announced
    1.54
     announce
    1.53
    Activations Density 0.092%

    No Known Activations