© 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. 2-GEMMASCOPE-RES-16K
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    information about academic affiliations and employment roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.72
    parsedMessage
    -0.71
    DataAnnotations
    -0.59
    queryInterface
    -0.57
    BASEPATH
    -0.56
    ioutil
    -0.51
    offsetof
    -0.51
    oprecip
    -0.50
     TextEditing
    -0.49
    rungsseite
    -0.49
    POSITIVE LOGITS
     rempliss
    0.71
     تضيفلها
    0.65
    šanai
    0.62
     henkil
    0.61
     dieux
    0.58
     Reſ
    0.56
     Chippewa
    0.56
     girth
    0.56
    yordu
    0.55
     šķ
    0.55
    Activations Density 1.824%

    No Known Activations