© 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. 6880
    Prev
    Next
    INDEX
    Explanations

    personal experiences and descriptions of challenges

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

    French text containing "j'ai" or "tu as"

    np_acts-logits-general · gemini-2.0-flash

    ai un

    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
    tvguidetime
    -0.79
    aarrggbb
    -0.77
     esternos
    -0.73
     المعيارى
    -0.73
    InjectAttribute
    -0.72
    ChildScrollView
    -0.71
    Personendaten
    -0.70
    setVerticalGroup
    -0.70
     متعلقه
    -0.70
    PropertyGroup
    -0.69
    POSITIVE LOGITS
    必要
    0.51
    zian
    0.43
     kyse
    0.42
    Fernsehserie
    0.41
     postIndex
    0.41
    getElementById
    0.39
    taba
    0.39
    need
    0.39
    好
    0.39
    先
    0.38
    Activations Density 0.060%

    No Known Activations