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. 1592
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific methods or studies

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

    Numerical lists, such as steps or options

    np_acts-logits-general · gemini-2.0-flash

    (closing_paren_or_period)

    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
     kaarangay
    -1.17
    JspWriter
    -1.00
    stateProvider
    -0.99
     estekak
    -0.98
    TagMode
    -0.97
     StatelessWidget
    -0.97
    CodeAttribute
    -0.89
    SourceChecksum
    -0.88
    MessageTagHelper
    -0.87
     ExecuteAsync
    -0.87
    POSITIVE LOGITS
     Lastly
    0.88
    Lastly
    0.86
     finally
    0.83
     lastly
    0.82
     Finally
    0.81
    Finally
    0.81
    その他
    0.81
     infine
    0.76
     Anything
    0.69
     other
    0.68
    Activations Density 0.255%

    No Known Activations