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. 8-GEMMASCOPE-RES-16K
    6. 5801
    Prev
    Next
    INDEX
    Explanations

    terms related to soil composition and fertility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.78
     utafitiHapana
    -0.72
     Monfieur
    -0.69
     étoit
    -0.69
    
    -0.68
     disambiguazione
    -0.67
     ainfi
    -0.65
    StoryboardSegue
    -0.65
     Efq
    -0.65
    XmlAccessType
    -0.64
    POSITIVE LOGITS
     soil
    1.05
     Soil
    0.93
    Soil
    0.92
    soil
    0.90
     soils
    0.80
    Soils
    0.77
     SOIL
    0.76
     Soils
    0.74
    SOIL
    0.73
    土壤
    0.63
    Activations Density 0.173%

    No Known Activations