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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4437
    Prev
    Next
    INDEX
    Explanations

    references to coercive actions and influences, particularly in legal contexts

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

    pressure or influence

    np_acts-logits-general · gemini-2.0-flash

    pressure and persuasion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.75
    CppMethod
    -0.70
    ThroughAttribute
    -0.60
     >=",
    -0.60
     [*]
    -0.59
    脚注の使い方
    -0.57
    Geplaatst
    -0.56
    SharedDtor
    -0.54
    RegistryLite
    -0.54
    ContentLoaded
    -0.52
    POSITIVE LOGITS
     pressure
    1.77
     persuasion
    1.59
     persuade
    1.56
     pressured
    1.56
     persuading
    1.55
    pressure
    1.54
    Pressure
    1.50
     Pressure
    1.46
     PRESSURE
    1.45
     persu
    1.45
    Activations Density 0.517%

    No Known Activations