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. 9658
    Prev
    Next
    INDEX
    Explanations

    meals and food quality descriptions

    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
    styleable
    -0.50
    minal
    -0.47
    OSIS
    -0.47
     existen
    -0.46
     trésor
    -0.46
    Butt
    -0.46
     Snack
    -0.45
    ėse
    -0.44
    haya
    -0.44
    estes
    -0.44
    POSITIVE LOGITS
     presentation
    0.76
     served
    0.70
    presentation
    0.69
     freshly
    0.64
     piping
    0.63
    Presentation
    0.62
     tasted
    0.61
     fresh
    0.61
     cooked
    0.61
     pesanan
    0.60
    Activations Density 0.062%

    No Known Activations