© 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. 36-GEMMASCOPE-RES-16K
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    references to violence or conflict involving authority figures

    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
     Autorisations
    -0.40
     Autorizaciones
    -0.36
    र्भ
    -0.35
    raulic
    -0.31
    ⎩
    -0.30
    /#{
    -0.29
     '__
    -0.29
    Ladd
    -0.29
    apt
    -0.28
     apt
    -0.28
    POSITIVE LOGITS
     للاسماء
    0.68
     killing
    0.67
     assassinated
    0.62
     indígen
    0.61
     assassination
    0.60
    Killing
    0.58
     surla
    0.58
     Geſ
    0.57
    DeleteMapping
    0.57
     houſe
    0.57
    Activations Density 0.055%

    No Known Activations