© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 29
    Prev
    Next
    INDEX
    Explanations

    words or phrases that include the prefix "un-."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.78
    ScopeManager
    -0.69
     الرياضيه
    -0.68
     disambiguazione
    -0.67
    sweise
    -0.66
    MemoryWarning
    -0.65
    WireFormatLite
    -0.64
    حياتها
    -0.64
    QMetaType
    -0.63
    verwijspagina
    -0.62
    POSITIVE LOGITS
     Un
    1.16
    Un
    1.09
     un
    1.06
     UN
    0.93
    un
    0.88
    UN
    0.71
     unen
    0.68
     unc
    0.67
    Uns
    0.67
     unf
    0.65
    Activations Density 0.171%

    No Known Activations