© 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. 15169
    Prev
    Next
    INDEX
    Explanations

    references to citations or source notes within the text

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

    Text within brackets, often unreadable or a reference

    np_acts-logits-general · gemini-2.0-flash

    references and citations

    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
     estekak
    -1.02
     Paglinawan
    -0.96
    WireFormatLite
    -0.92
    adaptiveStyles
    -0.90
     snippetHide
    -0.85
     otomatig
    -0.85
    InitVars
    -0.85
     numerus
    -0.82
     ویکی‌پدی
    -0.82
     propOrder
    -0.82
    POSITIVE LOGITS
    ↵↵
    0.59
    즉
    0.59
     It
    0.57
    Hence
    0.55
     The
    0.55
     That
    0.54
     Like
    0.54
     They
    0.53
     Hence
    0.53
    Like
    0.52
    Activations Density 0.441%

    No Known Activations