© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts related to data retrieval and user interface elements

    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
    NewUrlParser
    -0.96
    ceutical
    -0.70
    ourites
    -0.68
    webtoken
    -0.66
    tawesome
    -0.65
    OfBirth
    -0.62
    AxisSize
    -0.61
    giène
    -0.59
    inafter
    -0.59
    reuung
    -0.57
    POSITIVE LOGITS
    aimana
    0.71
    sterious
    0.66
    etheless
    0.57
     IBOutlet
    0.57
    selben
    0.52
    Obrázky
    0.50
    utenant
    0.49
    aporation
    0.48
    IBOutlet
    0.47
    دواج
    0.47
    Activations Density 1.967%

    No Known Activations