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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5611
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics

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

    Numbers within timestamps

    np_acts-logits-general · gemini-2.0-flash

    timestamps and timestamps -->

    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
     mergeFrom
    -0.75
     Италијани
    -0.66
    rrggbb
    -0.62
    ########.
    -0.61
    buttonBar
    -0.60
     Мексичка
    -0.60
    المشاركات
    -0.59
    calaure
    -0.59
    AndroidJUnit
    -0.59
     saites
    -0.58
    POSITIVE LOGITS
     useRouter
    0.71
     onwards
    0.64
     useNavigate
    0.56
    ⓧ
    0.56
    :✨
    0.53
    ýš
    0.52
    tvguidetime
    0.51
    UNRELATED
    0.49
     مشين
    0.48
    ollectionView
    0.48
    Activations Density 0.188%

    No Known Activations