© 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. 11-GEMMASCOPE-RES-16K
    11. 8466
    Prev
    Next
    INDEX
    Explanations

    references to unnecessary or redundant elements and the concept of excessiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.57
    parsedMessage
    -0.55
    SequentialGroup
    -0.50
    pecabe
    -0.48
     Italijanski
    -0.48
     nativo
    -0.47
    UnsafeEnabled
    -0.47
     preferido
    -0.46
     Audiodateien
    -0.44
    outWeight
    -0.44
    POSITIVE LOGITS
     unnecessary
    1.04
     useless
    1.00
     pointless
    0.98
     inutile
    0.98
     waste
    0.89
    Useless
    0.86
     superfluous
    0.85
    useless
    0.82
     wasted
    0.79
     inuti
    0.77
    Activations Density 0.621%

    No Known Activations