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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6165
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals, specifically focusing on "Physical Review" and its variations

    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
    reportWebVitals
    -0.76
    ylum
    -0.72
     okuyayım
    -0.72
    Personendaten
    -0.72
     Nier
    -0.70
     kasarigan
    -0.69
     calyx
    -0.68
    apimachinery
    -0.68
     autorytatywna
    -0.68
    complexType
    -0.67
    POSITIVE LOGITS
     reputation
    0.77
     Juice
    0.73
     juice
    0.71
    REV
    0.71
    juice
    0.70
     REV
    0.68
     Rev
    0.66
     fleet
    0.64
     المرجع
    0.63
    Juice
    0.63
    Activations Density 0.074%

    No Known Activations