© 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 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. 11055
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences related to identity and cultural interactions

    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
     apapun
    -0.73
    ArrowToggle
    -0.67
     quaisquer
    -0.65
     akár
    -0.62
     podendo
    -0.62
     enää
    -0.60
     любых
    -0.59
     any
    -0.58
     anything
    -0.58
     любые
    -0.57
    POSITIVE LOGITS
     recently
    0.83
     accidentally
    0.82
     iirc
    0.80
    たまたま
    0.80
     IIRC
    0.79
     someone
    0.77
     somebody
    0.77
    recently
    0.77
    someone
    0.71
    Someone
    0.70
    Activations Density 0.968%

    No Known Activations