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 Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10242
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical concepts, particularly those involving functions and mappings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.71
    grande
    -0.64
    autoreleasepool
    -0.63
     nakalista
    -0.61
    GEBURTSDATUM
    -0.61
    jsxFileName
    -0.60
    __':
    
    -0.58
    CloseOperation
    -0.58
    IndexOutOfBounds
    -0.53
     للمعارف
    -0.52
    POSITIVE LOGITS
     map
    0.83
     maps
    0.83
     mapping
    0.77
     Map
    0.72
     Maps
    0.71
    Map
    0.70
     composition
    0.68
    Maps
    0.67
    maps
    0.67
     mapa
    0.65
    Activations Density 2.293%

    No Known Activations