© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 267
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical notations and concepts, especially those related to functions and norms in a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical and function-related contexts

    np_acts-logits-general · gemini-2.0-flash

    functions, bounded, analytic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    tvguidetime
    -0.71
     betweenstory
    -0.69
    writeFieldEnd
    -0.65
     Vikipedi
    -0.65
     CreateTagHelper
    -0.64
     mergeFrom
    -0.62
    DrawerToggle
    -0.61
    Попис
    -0.61
     oprot
    -0.60
    şekkür
    -0.59
    POSITIVE LOGITS
     functions
    0.97
     funciones
    0.85
     function
    0.83
    functions
    0.81
     fonctions
    0.79
     Functions
    0.79
     FUNCTIONS
    0.73
    function
    0.73
     fonction
    0.73
     funzioni
    0.70
    Activations Density 1.980%

    No Known Activations