© 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. 18-GEMMASCOPE-RES-16K
    11. 10887
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceptions and limitations in legal or contractual contexts

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

    "Not" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    but not limited to, last but not least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.61
    Autoritní
    -0.56
     îns
    -0.56
    HasAnnotation
    -0.56
     فريبيس
    -0.55
    Hochspringen
    -0.55
    <>
    -0.54
    Floating
    -0.54
    fillType
    -0.54
     ***!
    -0.53
    POSITIVE LOGITS
     least
    0.97
    Least
    0.75
     Least
    0.74
    least
    0.70
     LEAST
    0.66
     limited
    0.62
     LIMITED
    0.59
     Limited
    0.57
    NUMX
    0.53
    UGHS
    0.52
    Activations Density 0.064%

    No Known Activations