© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1244
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.76
    verwijspagina
    -0.71
    NameInMap
    -0.70
     싶
    -0.69
     Спасибо
    -0.66
     initComponents
    -0.65
     Jacobi
    -0.64
    Dislikes
    -0.64
     forgiven
    -0.62
    Personensuche
    -0.62
    POSITIVE LOGITS
     simply
    0.60
     to
    0.59
    JspWriter
    0.55
    ที่จะ
    0.51
     completely
    0.49
    المشاركات
    0.49
     will
    0.47
     μην
    0.47
     MatDialog
    0.46
    zionalità
    0.45
    Activations Density 0.146%

    No Known Activations