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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13238
    Prev
    Next
    INDEX
    Explanations

    references to agricultural practices and collaborations

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

    after "University" or "of"

    np_acts-logits-general · gemini-2.0-flash

    University Extension

    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
    yntaxException
    -0.67
    OrNil
    -0.62
     שוליים
    -0.60
    PointerException
    -0.57
     snippetHide
    -0.56
    [:
    -0.55
    DoubleQuotes
    -0.54
    WebElementEntity
    -0.54
    ANNES
    -0.52
    LogFactory
    -0.51
    POSITIVE LOGITS
     Extension
    1.01
     extension
    1.00
    Extension
    0.90
    extension
    0.89
    xtension
    0.80
     EXTENSION
    0.80
    EXTENSION
    0.77
     extensión
    0.71
     exten
    0.70
     extensions
    0.66
    Activations Density 0.258%

    No Known Activations