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. 21-GEMMASCOPE-RES-16K
    6. 14679
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional statements and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.98
    tagHelperRunner
    -0.87
     تضيفلها
    -0.77
     mergeFrom
    -0.76
     myſelf
    -0.75
     Efq
    -0.73
    \}\\
    -0.72
    GEBURTSDATUM
    -0.72
    addCriterion
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
     empty
    0.72
    empty
    0.70
     count
    0.65
    count
    0.60
     in
    0.56
     class
    0.56
    isset
    0.52
    class
    0.49
     is
    0.48
    is
    0.47
    Activations Density 0.058%

    No Known Activations