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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16397
    Prev
    Next
    INDEX
    Explanations

    terms related to marine environments and marine life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    entibus
    -0.57
     Wikiseite
    -0.53
    slant
    -0.52
    zkopf
    -0.51
    ientôt
    -0.50
    SetId
    -0.50
     kna
    -0.50
    BibitemShut
    -0.50
     chapéu
    -0.49
     stockbild
    -0.49
    POSITIVE LOGITS
     Marine
    0.90
    Marine
    0.89
     marine
    0.78
     MARINE
    0.77
     Marin
    0.70
    marine
    0.68
     Marino
    0.68
    Marin
    0.66
     Marines
    0.59
     Maren
    0.59
    Activations Density 0.004%

    No Known Activations