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. 13664
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical conditions and scientific terminology

    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
    InvalidProtocol
    -0.67
     otomatig
    -0.65
    Hochspringen
    -0.64
     الاطلاع
    -0.62
    ftagPool
    -0.61
    #+#
    -0.60
     Penh
    -0.60
     Paglinawan
    -0.58
    utable
    -0.58
    numerusform
    -0.56
    POSITIVE LOGITS
    WebVitals
    0.59
     Juifs
    0.56
    exitRule
    0.56
     parati
    0.54
     }{@
    0.53
    "]:
    0.52
    astify
    0.52
     }</
    0.51
    `),
    0.50
    )";
    
    0.50
    Activations Density 0.430%

    No Known Activations