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. 16-GEMMASCOPE-RES-16K
    6. 3181
    Prev
    Next
    INDEX
    Explanations

    biological terms and references related to health conditions and genetic research

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

    Numbers within identifiers (e.g., "C20orf201")

    np_acts-logits-general · gemini-2.0-flash

    C20orf gene identifiers

    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
    DBNull
    -0.60
    AnchorStyles
    -0.58
    IPAC
    -0.58
    complexContent
    -0.57
    RTSN
    -0.57
     nahilalakip
    -0.57
    CloseOperation
    -0.56
    FontStyle
    -0.54
    disposing
    -0.54
    MenuInflater
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.83
     تضيفلها
    0.64
     GenerationType
    0.62
     становника
    0.61
     Vaticano
    0.59
     propOrder
    0.57
     chrétiens
    0.55
     bună
    0.54
    ătoare
    0.53
    aarrggbb
    0.52
    Activations Density 1.528%

    No Known Activations