© 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. 3-GEMMASCOPE-RES-16K
    11. 1174
    Prev
    Next
    INDEX
    Explanations

    terms related to protective or preventive measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.90
     Lesnar
    -0.86
     OMITBAD
    -0.80
     odeur
    -0.80
     препратки
    -0.75
    InSection
    -0.75
    ulink
    -0.74
    ToScroll
    -0.72
     CiNii
    -0.72
    URLException
    -0.70
    POSITIVE LOGITS
    ative
    1.74
    ATIVE
    1.48
    rative
    1.43
    sive
    1.35
    tive
    1.30
    lective
    1.29
     destructive
    1.29
     reflective
    1.26
     supportive
    1.26
     predictive
    1.26
    Activations Density 0.259%

    No Known Activations