© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5868
    Prev
    Next
    INDEX
    Explanations

    polite requests or imperative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Requests or politeness markers

    np_acts-logits-general · gemini-2.0-flash

    initiating polite requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.59
     AssemblyTitle
    -0.57
     AppComponent
    -0.50
    ViewImports
    -0.49
    MCM
    -0.48
     NCP
    -0.48
     initComponents
    -0.47
    CppMethod
    -0.47
    SharedCtor
    -0.46
    Occupation
    -0.46
    POSITIVE LOGITS
     please
    1.78
    please
    1.70
     Please
    1.68
    Please
    1.67
     Bitte
    1.38
     PLEASE
    1.37
    PLEASE
    1.35
    Bitte
    1.34
     bitte
    1.30
    请
    1.09
    Activations Density 0.074%

    No Known Activations