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. 1-GEMMASCOPE-RES-16K
    6. 14954
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation functions and references related to elements and liver in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.55
    Discografia
    -0.54
    نجی
    -0.48
     Trainers
    -0.48
    SdkVersion
    -0.47
    MNA
    -0.47
    jeka
    -0.46
     ttk
    -0.46
    Життєпис
    -0.45
    WriteTagHelper
    -0.45
    POSITIVE LOGITS
    getElementById
    0.83
    ]--;
    0.82
    WindowConstants
    0.81
     liability
    0.67
    principalTable
    0.64
    elemField
    0.64
    queryInterface
    0.64
    JScrollPane
    0.62
     engraçadas
    0.62
    ItemLayout
    0.62
    Activations Density 0.087%

    No Known Activations