© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8729
    Prev
    Next
    INDEX
    Explanations

    references to the Roman Empire and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.63
     Efq
    -0.60
     Majefty
    -0.60
     Monfieur
    -0.59
    delwed
    -0.59
     Eſ
    -0.59
     stockbild
    -0.58
     lenker
    -0.57
     RoutedEventArgs
    -0.57
     Theſe
    -0.57
    POSITIVE LOGITS
     romanos
    0.65
     Roman
    0.63
    Roman
    0.54
    ladiator
    0.52
     romano
    0.51
     ROMAN
    0.51
    Romans
    0.48
     romana
    0.47
     Romans
    0.47
     рим
    0.47
    Activations Density 0.163%

    No Known Activations