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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8335
    Prev
    Next
    INDEX
    Explanations

    references to "a" as a structural marker in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ti
    -0.61
    uh
    -0.59
    k
    -0.58
    inn
    -0.57
    pen
    -0.57
    hit
    -0.57
    field
    -0.57
     pinulongan
    -0.57
    স্ত
    -0.56
    itt
    -0.55
    POSITIVE LOGITS
     للمعارف
    0.94
    sebagai
    0.87
    Sebagai
    0.81
    webElementXpaths
    0.80
    enumii
    0.78
     DialogResult
    0.77
     jako
    0.77
    jako
    0.76
    jercicios
    0.76
     ramach
    0.75
    Activations Density 0.116%

    No Known Activations