© 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. 16-GEMMASCOPE-RES-16K
    6. 7244
    Prev
    Next
    INDEX
    Explanations

    programming language keywords related to asynchronous tasks and testing

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

    Follows specific symbols or words like "Q:" or "\"

    np_acts-logits-general · gemini-2.0-flash

    McCarthy and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.71
     >=",
    -0.69
    setVerticalGroup
    -0.68
    oredCriteria
    -0.67
     Réponses
    -0.66
     Normdatei
    -0.65
     للمعارف
    -0.61
     newBuilder
    -0.61
    цездатний
    -0.60
    +#+#
    -0.58
    POSITIVE LOGITS
    WebServlet
    0.55
    hdys
    0.54
    SneakyThrows
    0.52
    IRUS
    0.52
    IBOutlet
    0.50
    udahkan
    0.49
    teborg
    0.48
    icana
    0.45
    كد
    0.45
     drauf
    0.43
    Activations Density 0.019%

    No Known Activations