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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13669
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or pathway

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.77
    ricts
    -0.75
    icias
    -0.70
     BEA
    -0.69
     Masa
    -0.69
     Barnet
    -0.68
    Cubit
    -0.68
     Poznań
    -0.67
     peric
    -0.66
     Signor
    -0.66
    POSITIVE LOGITS
     down
    0.77
     оригіналу
    0.77
     المعيارى
    0.75
    Externí
    0.73
     through
    0.69
     satunya
    0.69
     across
    0.69
     up
    0.68
     lượt
    0.65
    chemin
    0.65
    Activations Density 0.005%

    No Known Activations