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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9691
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to food ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andre
    -0.41
    frc
    -0.40
    一步
    -0.38
    ً
    -0.38
     Bef
    -0.37
    jed
    -0.36
     medes
    -0.36
     forget
    -0.36
     taş
    -0.36
    hide
    -0.36
    POSITIVE LOGITS
     betweenstory
    0.99
    WithIOException
    0.97
    parsedMessage
    0.95
    MethodManager
    0.94
     CreateTagHelper
    0.90
     <=",
    0.89
    setVerticalGroup
    0.89
    djangoproject
    0.88
    ThroughAttribute
    0.86
    ItemBackground
    0.86
    Activations Density 0.457%

    No Known Activations