Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1536
    Prev
    Next
    INDEX
    Explanations

    references to healthcare policies or organizations

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

    Comes after Q or similar punctuations

    np_acts-logits-general · gemini-2.0-flash

    verbally advised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.70
    Bronnen
    -0.64
    */].
    -0.56
    IndentedString
    -0.53
    elemField
    -0.50
    ipedi
    -0.47
     pylab
    -0.47
    økt
    -0.46
    存于互联网档案馆
    -0.46
    printStackTrace
    -0.46
    POSITIVE LOGITS
    ConstraintMaker
    0.92
     how
    0.83
     what
    0.76
    IntoConstraints
    0.67
     why
    0.67
     bluntly
    0.65
     plainly
    0.61
     verbally
    0.59
    ScopeManager
    0.58
     about
    0.58
    Activations Density 0.130%

    No Known Activations