© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 10107
    Prev
    Next
    INDEX
    Explanations

    the use of verbs indicating action or execution in processes or activities

    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
    exitRule
    -0.41
     Economía
    -0.39
     ľ
    -0.38
     newBuilder
    -0.37
     gouver
    -0.37
     gober
    -0.35
     Kollegen
    -0.35
     emprego
    -0.35
     budgets
    -0.35
     подо
    -0.35
    POSITIVE LOGITS
     yapılan
    0.69
     ongoing
    0.66
     عمليات
    0.61
    ongoing
    0.60
     undertook
    0.60
     rigorous
    0.59
     extensive
    0.59
    romptu
    0.58
    การ
    0.57
     عملية
    0.57
    Activations Density 0.783%

    No Known Activations