© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in numerical or quantitative data

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

    Numbers followed by periods and other numbers

    np_acts-logits-general · gemini-2.0-flash

    scientific numbers and citations

    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
     ProtoMessage
    -0.66
     aastal
    -0.65
     تضيفلها
    -0.63
     محفوظة
    -0.60
    BagLayout
    -0.58
     HasFactory
    -0.56
    ReusableCell
    -0.56
    twas
    -0.54
     الحره
    -0.54
    lwjgl
    -0.54
    POSITIVE LOGITS
    prava
    0.53
    ogada
    0.47
     Reverso
    0.46
     "..\..\..\
    0.46
     eerder
    0.45
    EndInit
    0.45
    roek
    0.45
    ibos
    0.45
    別の
    0.44
    ropractor
    0.44
    Activations Density 1.642%

    No Known Activations