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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    formal language related to legal documents and procedures

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

    Preceding "shall," "must," or similar legal terms

    np_acts-logits-general · gemini-2.0-flash

    shall, should, must

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.82
    Portail
    -0.70
    larg
    -0.63
    Portale
    -0.62
    awtextra
    -0.60
    LayoutStyle
    -0.59
    ThroughAttribute
    -0.59
    MigrationBuilder
    -0.58
    thanks
    -0.57
     thanks
    -0.56
    POSITIVE LOGITS
     shall
    1.02
    shall
    0.88
     SHALL
    0.69
     must
    0.66
     Any
    0.65
     any
    0.64
    不得
    0.64
    }`).
    0.63
     should
    0.62
     Shall
    0.60
    Activations Density 0.410%

    No Known Activations