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. 11-GEMMASCOPE-RES-16K
    6. 13135
    Prev
    Next
    INDEX
    Explanations

    references to diversity or variety within a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gameserver
    -0.72
    ئيس
    -0.69
     bres
    -0.62
     Läng
    -0.61
    icho
    -0.60
    بوابة
    -0.59
    ternal
    -0.58
    DotNetBar
    -0.58
     чем
    -0.58
    rachtet
    -0.57
    POSITIVE LOGITS
     تضيفلها
    0.84
    Bunch
    0.83
    randomUUID
    0.81
     ряда
    0.79
     ряд
    0.79
     bunch
    0.77
     Bunch
    0.77
     variety
    0.75
    upaten
    0.74
     multitud
    0.73
    Activations Density 0.116%

    No Known Activations