© 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. 33-GEMMASCOPE-RES-16K
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    references to different types of mucoidal substances or compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.49
     Exacts
    -0.48
    RegressionTest
    -0.46
     oído
    -0.43
    ViewInit
    -0.43
     computadoras
    -0.42
     Meksiku
    -0.42
    Microkernel
    -0.41
    NameInMap
    -0.40
     banderas
    -0.40
    POSITIVE LOGITS
     Mu
    0.71
    Mu
    0.66
     mu
    0.55
    帖最后由
    0.47
    Му
    0.46
     MU
    0.45
    mu
    0.45
    Muz
    0.45
     Mug
    0.42
     Muir
    0.41
    Activations Density 0.348%

    No Known Activations