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

    Neuronpedia

    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. 27-GEMMASCOPE-RES-16K
    11. 9665
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    省市镇
    -0.44
     навіть
    -0.35
     EVEN
    -0.35
     even
    -0.34
     даже
    -0.34
    AutoField
    -0.34
    ParallelGroup
    -0.33
     anyway
    -0.33
     '{@
    -0.33
    even
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.65
     autorytatywna
    0.65
     otomatig
    0.53
    новниш
    0.52
     kaarangay
    0.51
     ویکی‌پدی
    0.51
    glLoadIdentity
    0.50
    同様に
    0.50
     незавершена
    0.50
    featureID
    0.49
    Activations Density 0.357%

    No Known Activations