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. 103061
    Prev
    Next
    INDEX
    Explanations

    references to food items and their preparation methods

    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
    jsxFileName
    -0.32
     armour
    -0.31
     nawr
    -0.30
    èdia
    -0.29
    MemoryWarning
    -0.28
     Raub
    -0.28
     armor
    -0.28
     getField
    -0.28
     herz
    -0.28
     pieles
    -0.27
    POSITIVE LOGITS
     BorderSide
    0.73
    IntoConstraints
    0.69
     lengths
    0.69
    niſſe
    0.68
    SBATCH
    0.67
    prefixer
    0.67
    XmlAccessType
    0.67
    iſchen
    0.66
    aragus
    0.66
    ArrowToggle
    0.65
    Activations Density 0.023%

    No Known Activations