© 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. 22-GEMMASCOPE-RES-16K
    11. 8363
    Prev
    Next
    INDEX
    Explanations

    numerical values related to API request parameters or results

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

    Follows "did" or "new"

    np_acts-logits-general · gemini-2.0-flash

    past, happening, and new items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.51
     scoper
    -0.45
     dentaire
    -0.44
     setw
    -0.43
     lasciare
    -0.41
     numai
    -0.41
     boî
    -0.41
     élect
    -0.41
     overras
    -0.41
    UMES
    -0.41
    POSITIVE LOGITS
     etc
    0.93
    etc
    0.78
    DockStyle
    0.71
    Hochspringen
    0.69
    pexpr
    0.67
     فريبيس
    0.66
    **,
    0.65
    ³,
    0.65
    …).
    0.64
     jScrollPane
    0.64
    Activations Density 0.112%

    No Known Activations