© 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. 5584
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to machinery and engineering processes

    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
    ParallelGroup
    -0.33
     NUKAT
    -0.29
    Bronnen
    -0.29
     doInBackground
    -0.29
    гія
    -0.29
    ClCompile
    -0.28
    itale
    -0.27
    rodalom
    -0.27
     iVar
    -0.26
    oznam
    -0.26
    POSITIVE LOGITS
     regularly
    3.06
     frequent
    2.66
     Regularly
    2.55
     regelmäßig
    2.50
     регулярно
    2.45
     periodically
    2.45
     regular
    2.39
     pravidel
    2.39
    frequent
    2.36
     periodic
    2.33
    Activations Density 1.486%

    No Known Activations