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. 36562
    Prev
    Next
    INDEX
    Explanations

    references to the state of Utah

    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
    Tikang
    -0.84
    BASEPATH
    -0.83
    pyplot
    -0.74
    hical
    -0.73
    afone
    -0.73
    derry
    -0.71
     EXE
    -0.71
    ynb
    -0.69
    MCD
    -0.68
     pardoned
    -0.67
    POSITIVE LOGITS
     Utah
    1.92
    Utah
    1.71
     utah
    1.32
     Mormon
    1.21
     LDS
    1.13
     Salt
    1.09
    utah
    1.02
     Mormons
    0.98
    Salt
    0.91
     Provo
    0.90
    Activations Density 0.049%

    No Known Activations