© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14258
    Prev
    Next
    INDEX
    Explanations

    references to food items and culinary elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usercontent
    -0.71
    bootstrapcdn
    -0.69
    TargetException
    -0.69
    ruptedException
    -0.64
    WithFormat
    -0.63
    yntaxException
    -0.62
    таратура
    -0.60
    mtrl
    -0.58
    wapV
    -0.57
    copg
    -0.56
    POSITIVE LOGITS
     Jerusalén
    0.40
     Geſ
    0.40
     autorytatywna
    0.40
    })*/
    0.39
     Jefus
    0.38
     faſt
    0.37
     enfans
    0.37
     kapture
    0.37
     ainfi
    0.37
     miniaturka
    0.36
    Activations Density 13.103%

    No Known Activations