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. 3-GEMMASCOPE-RES-16K
    6. 10084
    Prev
    Next
    INDEX
    Explanations

    terms related to viruses and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ski
    -0.88
     Ski
    -0.87
    Nordic
    -0.85
     skier
    -0.84
     Arctic
    -0.83
     skis
    -0.83
     reindeer
    -0.81
    ☃
    -0.81
     Nordic
    -0.81
     Snow
    -0.80
    POSITIVE LOGITS
     Cleopatra
    0.73
    Osaka
    0.67
    ніципалі
    0.66
    Enders
    0.64
     vapeur
    0.63
    iotensin
    0.63
     bụ
    0.63
    strij
    0.62
    Tikang
    0.61
     Igbo
    0.61
    Activations Density 1.638%

    No Known Activations