© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9995
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and legal authority within a governmental context

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

    after names, especially Rajapaksa/Bandaranayake

    np_acts-logits-general · gemini-2.0-flash

    Ranil Wickremesinghe and Sri Lankan politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.67
    esgue
    -0.66
     zależy
    -0.62
    AddHtmlAttribute
    -0.60
    ритори
    -0.59
    eabouts
    -0.59
     OnInit
    -0.58
    }\]
    -0.58
    σίας
    -0.57
     Sri
    -0.57
    POSITIVE LOGITS
     Arach
    0.52
    WireFormat
    0.47
     Jay
    0.46
     уда
    0.43
    CGRectMake
    0.42
    ابه
    0.42
    Questa
    0.41
    ragen
    0.41
    Citation
    0.41
    ValueGenerated
    0.41
    Activations Density 0.090%

    No Known Activations