© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 5310
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resten
    -0.70
    Others
    -0.64
     sekitarnya
    -0.60
     Others
    -0.59
     دیگران
    -0.57
     others
    -0.56
     المزيد
    -0.52
     serupa
    -0.51
     Subsequent
    -0.50
     subsequent
    -0.50
    POSITIVE LOGITS
     other
    1.06
    autre
    0.88
    other
    0.87
    OTHER
    0.82
     OTHER
    0.81
    ther
    0.80
     Other
    0.75
    THER
    0.71
     autre
    0.70
     ther
    0.69
    Activations Density 0.289%

    No Known Activations