© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4614
    Prev
    Next
    INDEX
    Explanations

    terms related to legal frameworks and principles

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

    "Means" or "mechanism" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    ways and means

    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
    ViewFeatures
    -0.71
    aarrggbb
    -0.71
    ISupport
    -0.66
    TagMode
    -0.66
    etton
    -0.61
    CompilerServices
    -0.57
    hoeddwyd
    -0.57
     continúas
    -0.57
    XmlAccessorType
    -0.56
    WebControls
    -0.56
    POSITIVE LOGITS
     used
    1.15
     whereby
    1.06
     employed
    1.04
     Used
    0.96
    used
    0.93
    Used
    0.92
    employed
    0.88
     utilized
    0.82
     USED
    0.81
     adopted
    0.78
    Activations Density 0.522%

    No Known Activations