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. 43449
    Prev
    Next
    INDEX
    Explanations

    various forms of action or processes, particularly those involving participation or medical contexts

    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
    Autoritní
    -0.78
    ChildScrollView
    -0.75
    enumii
    -0.70
    Становништво
    -0.69
     NSCoder
    -0.65
     насељу
    -0.64
    Дереккөздер
    -0.64
     виправивши
    -0.63
     estekak
    -0.63
     Roskov
    -0.62
    POSITIVE LOGITS
     ogóle
    0.52
     kasarigan
    0.50
     osoba
    0.48
    muerzo
    0.48
     outdoors
    0.47
     personer
    0.46
    árol
    0.45
    simage
    0.44
    nalités
    0.43
     person
    0.43
    Activations Density 0.325%

    No Known Activations