© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2189
    Prev
    Next
    INDEX
    Explanations

    content related to figures, tables, and supplemental information in research documents

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

    supporting figures/tables

    np_acts-logits-general · gemini-2.0-flash

    supplementary figures and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.62
     саны
    -0.58
     Wikimedijinoj
    -0.57
    BuilderFactory
    -0.53
    GetMapping
    -0.52
    ddots
    -0.50
    uegos
    -0.48
    oredCriteria
    -0.47
     Roskov
    -0.47
    WEBPACK
    -0.47
    POSITIVE LOGITS
     supplementary
    1.27
     Supplementary
    1.22
     supplemental
    1.11
    Supplementary
    1.11
     Supplemental
    1.10
    Supplemental
    1.08
    SUPPLEMENT
    1.02
     appendix
    0.98
     SUPPLEMENT
    0.98
     Appendix
    0.97
    Activations Density 2.022%

    No Known Activations