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. 14710
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expressions or sentiments in a text

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

    Follows ellipses or incomplete quotes

    np_acts-logits-general · gemini-2.0-flash

    enhance sentence

    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
    enderror
    -0.72
    expiresIn
    -0.60
    iprot
    -0.51
    wnia
    -0.50
    jelen
    -0.48
    annica
    -0.48
     المعرف
    -0.48
    curity
    -0.47
    </strong>
    -0.47
    viewDidLoad
    -0.46
    POSITIVE LOGITS
     […]
    1.14
    <eos>
    1.01
    
    0.99
    Continue
    0.94
    請繼續往下閱讀
    0.86
     [...]
    0.82
    Показать
    0.81
    […]
    0.80
    [...]
    0.80
    ,...
    0.77
    Activations Density 0.365%

    No Known Activations