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. 10-GEMMASCOPE-RES-16K
    6. 5133
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance and player achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esterday
    -0.69
    MENAFN
    -0.65
    parsedMessage
    -0.65
    MethodManager
    -0.63
    AutoresizingMask
    -0.62
     mxArray
    -0.61
     JScrollPane
    -0.60
     AssemblyTitle
    -0.59
     INTERESAR
    -0.58
    migrationBuilder
    -0.58
    POSITIVE LOGITS
     lifetime
    0.66
    TagMode
    0.59
    BeginContext
    0.57
     accumulation
    0.55
     cumulative
    0.55
     accumulated
    0.55
     Insgesamt
    0.52
    Демографія
    0.51
     acumula
    0.51
     Accumulation
    0.50
    Activations Density 0.257%

    No Known Activations