© 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. 14991
    Prev
    Next
    INDEX
    Explanations

    specific instructions or recommendations related to technical procedures and maintenance

    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
    whereas
    -0.73
     debido
    -0.70
    SequentialGroup
    -0.68
    astify
    -0.68
    Whereas
    -0.67
     devido
    -0.67
     بسبب
    -0.66
    due
    -0.65
    hence
    -0.64
     благодаря
    -0.63
    POSITIVE LOGITS
     yourself
    1.20
     preferably
    1.09
     your
    0.92
     carefully
    0.88
    preferably
    0.83
    yourself
    0.79
     YOURSELF
    0.76
     yourselves
    0.76
    your
    0.71
     Yourself
    0.70
    Activations Density 0.470%

    No Known Activations