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. 36600
    Prev
    Next
    INDEX
    Explanations

    repeated uses of the definite article "the."

    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
    BeginContext
    -0.78
     LoggerFactory
    -0.77
    }")
    
    -0.71
     surla
    -0.71
    ISupport
    -0.71
    addCriterion
    -0.70
     <<<<<<<<<<<<<<
    -0.69
    DockStyle
    -0.69
    webElementGuid
    -0.68
    TypedDataSet
    -0.66
    POSITIVE LOGITS
     mesmas
    0.50
     fenomeno
    0.49
     mismas
    0.49
     medesimo
    0.45
     same
    0.44
     mismos
    0.44
     įsi
    0.43
    Dữ
    0.42
    føl
    0.41
    occasione
    0.41
    Activations Density 0.124%

    No Known Activations