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-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 433
    Prev
    Next
    INDEX
    Explanations

    substantive phrases related to kidney health and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]="
    -0.70
     وتسجيلات
    -0.70
     
    -0.69
    ("%.
    -0.66
    TIMORE
    -0.66
     Angeli
    -0.63
     squir
    -0.63
    ']}
    -0.62
    "]}
    -0.61
     Della
    -0.60
    POSITIVE LOGITS
    InjectAttribute
    0.65
     roligt
    0.63
    InjectMocks
    0.62
    AlterField
    0.60
     iesp
    0.59
    styleType
    0.58
     voorbeeld
    0.58
     vantaggio
    0.57
    šė
    0.57
     part
    0.56
    Activations Density 0.006%

    No Known Activations