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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7784
    Prev
    Next
    INDEX
    Explanations

    references to "Candy" and related terms, particularly in the context of discussions or studies involving Candida

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Candy" and misspellings of it

    np_acts-logits-general · gemini-2.0-flash

    Candy + word, Pant + word

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     StatelessWidget
    -0.80
     estekak
    -0.79
    ThroughAttribute
    -0.72
    ⓧ
    -0.72
    Попис
    -0.67
    feira
    -0.66
    PhysRevD
    -0.65
     StatefulWidget
    -0.63
    hesda
    -0.62
    aarrggbb
    -0.62
    POSITIVE LOGITS
     Shaksp
    0.60
    voort
    0.56
     schlecht
    0.55
    Intrinsic
    0.54
     تضيفلها
    0.54
     Protobuf
    0.54
    orteur
    0.53
     Eres
    0.53
    timbangan
    0.52
    ANGAN
    0.52
    Activations Density 0.457%

    No Known Activations