© 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. 20-GEMMASCOPE-RES-16K
    11. 11228
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to class definitions and method declarations

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

    Followed by "super" or "Super"

    np_acts-logits-general · gemini-2.0-flash

    calling super constructor

    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
     kasarigan
    -0.77
    évaluateur
    -0.74
    protoimpl
    -0.69
     ddelweddau
    -0.67
     للاسماء
    -0.67
    tvguidetime
    -0.67
    Попис
    -0.66
    aarrggbb
    -0.66
     Վերցված
    -0.66
     incomplète
    -0.66
    POSITIVE LOGITS
    super
    1.09
     super
    0.98
     [
    0.56
    Object
    0.55
     Super
    0.53
    Super
    0.52
    let
    0.51
     Object
    0.51
    超级
    0.50
     супер
    0.47
    Activations Density 0.103%

    No Known Activations