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

    Neuronpedia

    Jacobian LensNEW
    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. 6234
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their properties in a programming context

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

    Code related to setting text properties

    np_acts-logits-general · gemini-2.0-flash

    setting label text or visibility

    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
    mybatisplus
    -0.63
    Portail
    -0.57
    хьтан
    -0.56
     externi
    -0.52
    tschaft
    -0.51
    χρι
    -0.51
     OFDb
    -0.50
     compro
    -0.49
     виправивши
    -0.49
    pushFollow
    -0.47
    POSITIVE LOGITS
    AutoSize
    0.75
     JLabel
    0.69
    LookAnd
    0.69
     QLabel
    0.63
    QLabel
    0.63
    ")));
    0.60
    JLabel
    0.58
     labels
    0.58
    jLabel
    0.55
    ">—
    0.55
    Activations Density 0.009%

    No Known Activations