© 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. 37-GEMMASCOPE-RES-16K
    11. 693
    Prev
    Next
    INDEX
    Explanations

    methods and actions aimed at prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.54
    (!__
    -0.53
    cleaning
    -0.48
     cleaned
    -0.47
    cleaned
    -0.47
    Either
    -0.47
     Giang
    -0.46
     Everywhere
    -0.46
     Examinations
    -0.44
     cleansed
    -0.44
    POSITIVE LOGITS
     future
    0.77
     terjadinya
    0.74
     unnecessary
    0.74
     unwanted
    0.73
     sorpresas
    0.69
     futuros
    0.69
     futuras
    0.68
     posibles
    0.67
     eventuali
    0.66
     accidental
    0.65
    Activations Density 0.600%

    No Known Activations