© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses and their associated conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.78
     Cæsar
    -0.62
     propOrder
    -0.57
     MaterialApp
    -0.55
     gyhoeddwyd
    -0.54
     Sopho
    -0.51
     Spenser
    -0.49
     Llor
    -0.48
     <>",
    -0.47
    ramide
    -0.46
    POSITIVE LOGITS
    /#{
    0.84
     StringTokenizer
    0.75
    sizeCache
    0.71
    if
    0.71
    elsif
    0.69
    Tembelea
    0.68
    TextUtils
    0.66
     MainAxisSize
    0.66
    帖最后由
    0.66
    |}{$
    0.65
    Activations Density 0.054%

    No Known Activations