© 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 EvalsExportsinterp-engineNEWAPI 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. 2767
    Prev
    Next
    INDEX
    Explanations

    words associated with unnatural or artificial conditions

    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
    TagMode
    -0.62
    HtmlAttribute
    -0.56
    WithIdentifier
    -0.55
     μην
    -0.54
    Puss
    -0.53
     prove
    -0.53
     Arxivat
    -0.52
    InetAddress
    -0.51
    putchar
    -0.51
     tantum
    -0.50
    POSITIVE LOGITS
     unnatural
    0.77
    لكتر
    0.69
    unusual
    0.62
     unusual
    0.61
    Abnormal
    0.60
    Dtor
    0.60
    Unusual
    0.60
    InitVars
    0.58
     Unusual
    0.57
     unconventional
    0.57
    Activations Density 0.456%

    No Known Activations