Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6610
    Prev
    Next
    INDEX
    Explanations

    components and ingredients commonly associated with food items, particularly in salads and sandwiches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -1.01
    SourceChecksum
    -1.01
    UnusedPrivate
    -0.88
    TargetException
    -0.85
     utafitiHapana
    -0.84
    MLLoader
    -0.84
    Gön
    -0.80
    contentLoaded
    -0.75
    DotNetBar
    -0.74
     iNdEx
    -0.74
    POSITIVE LOGITS
     dressing
    1.06
     salad
    1.03
    dressing
    0.92
     Dressing
    0.90
     Salad
    0.89
    Dressing
    0.87
     dressings
    0.83
     salads
    0.82
    Salad
    0.80
     DRESS
    0.77
    Activations Density 0.088%

    No Known Activations