© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of obligation or conditions regarding actions

    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
     Progres
    -0.53
     potuto
    -0.51
    onomous
    -0.49
     الاع
    -0.46
    ViewFeatures
    -0.46
     voce
    -0.46
    text
    -0.45
    porte
    -0.45
     sexuality
    -0.45
    webkit
    -0.44
    POSITIVE LOGITS
     Italijani
    0.88
     Administrativna
    0.87
    rmızı
    0.79
    NGC
    0.76
    GEBURTSDATUM
    0.75
    protoimpl
    0.74
    曖昧さ回避
    0.70
    onAttach
    0.70
    !”.
    0.68
    !».
    0.68
    Activations Density 0.047%

    No Known Activations