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. 130975
    Prev
    Next
    INDEX
    Explanations

    references to primary care and related healthcare terminology

    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
    Rüyada
    -0.67
     getItemCount
    -0.63
     getVersion
    -0.60
    áctenos
    -0.60
     FileNotFound
    -0.59
     getDate
    -0.58
     handleChange
    -0.58
    SBATCH
    -0.57
    สึก
    -0.57
     edição
    -0.56
    POSITIVE LOGITS
     primary
    1.15
     Primary
    1.13
    Primary
    1.04
     PRIMARY
    1.02
    primary
    0.96
    PRIMARY
    0.88
     primario
    0.77
     principal
    0.73
     primaria
    0.73
    PrimaryKey
    0.72
    Activations Density 0.019%

    No Known Activations