© 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. 16-GEMMASCOPE-RES-16K
    11. 2725
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing the necessity or obligation of actions

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

    Follows "should be"

    np_acts-logits-general · gemini-2.0-flash

    what should be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.83
    yntaxException
    -0.82
    ViewFeatures
    -0.75
    SequentialGroup
    -0.74
    abestanden
    -0.71
    CodedInputStream
    -0.70
    WebVitals
    -0.69
     AssemblyCulture
    -0.68
    TagMode
    -0.67
    ]")]
    -0.66
    POSITIVE LOGITS
     be
    0.71
     should
    0.70
     absolument
    0.63
     consideration
    0.60
    should
    0.59
     ASAP
    0.58
     Deber
    0.58
     обязательно
    0.56
    kmäler
    0.55
     assolutamente
    0.55
    Activations Density 0.341%

    No Known Activations