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. 16098
    Prev
    Next
    INDEX
    Explanations

    elements related to events and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    physical objects or places

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     (
    -0.51
    class
    -0.45
     The
    -0.43
    aları
    -0.43
     B
    -0.43
    like
    -0.43
     class
    -0.42
     is
    -0.42
     Single
    -0.41
     Po
    -0.41
    POSITIVE LOGITS
    CloseOperation
    1.14
    featureID
    0.96
    IntoConstraints
    0.90
     Paglinawan
    0.85
    WebControls
    0.82
    :✨
    0.81
    rrggbb
    0.81
    MemoryWarning
    0.80
    ClientRect
    0.79
    脚注の使い方
    0.78
    Activations Density 0.484%

    No Known Activations