© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15753
    Prev
    Next
    INDEX
    Explanations

    concepts related to recovery and restoration in various contexts

    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
    PositiveButton
    -0.44
     further
    -0.41
     ulteriori
    -0.35
     unterschied
    -0.35
     resulting
    -0.34
     tambahan
    -0.34
     beyond
    -0.33
    further
    -0.33
     Hintergrund
    -0.33
     different
    -0.33
    POSITIVE LOGITS
     normalcy
    0.97
     normality
    0.96
     lost
    0.82
     normalidad
    0.80
    lost
    0.79
     semula
    0.78
    原来的
    0.75
     original
    0.75
     Lost
    0.72
     eski
    0.70
    Activations Density 0.379%

    No Known Activations