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. 19-GEMMASCOPE-RES-16K
    6. 2109
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and data characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.66
    İstinadlar
    -0.64
    ftagPool
    -0.62
    Xna
    -0.59
    aarrggbb
    -0.58
    ImageField
    -0.57
    jspx
    -0.57
     actionTypes
    -0.56
     चीज़ों
    -0.56
    InjectAttribute
    -0.54
    POSITIVE LOGITS
     for
    1.23
    สำหรับ
    1.02
     עבור
    0.98
    针对
    0.93
    針對
    0.91
     corresponding
    0.89
     untuk
    0.88
    对于
    0.87
    for
    0.87
     für
    0.85
    Activations Density 1.296%

    No Known Activations