Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13063
    Prev
    Next
    INDEX
    Explanations

    references to governmental positions, specifically related to secretaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ípios
    -0.71
     Cand
    -0.69
    inander
    -0.65
    ある
    -0.64
    xffffffff
    -0.63
    шое
    -0.63
     Accesat
    -0.63
    QApplication
    -0.62
    DebuggerStep
    -0.62
    :✨
    -0.61
    POSITIVE LOGITS
     Secretary
    3.17
     secretary
    3.04
    Secretary
    2.90
     SECRETARY
    2.88
     secretaries
    2.67
    secretary
    2.58
     Secretaries
    2.53
     secrétaire
    2.04
     secretario
    1.87
     Secrétaire
    1.84
    Activations Density 0.080%

    No Known Activations