© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "please" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.84
    الإنجليزية
    -0.80
    Personendaten
    -0.71
     Nullable
    -0.66
     Савезне
    -0.65
    ThroughAttribute
    -0.64
     ostavi
    -0.63
     Efq
    -0.63
    endphp
    -0.62
     createContext
    -0.61
    POSITIVE LOGITS
    Please
    1.48
     Please
    1.43
    Kindly
    0.94
    PLEASE
    0.92
    Veuillez
    0.90
     Veuillez
    0.85
     Bitte
    0.83
     Kindly
    0.81
     We
    0.77
    please
    0.77
    Activations Density 0.195%

    No Known Activations