© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 22068
    Prev
    Next
    INDEX
    Explanations

    terms related to reputation and medical malpractice

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

    bad accusations and claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optionalTypeArgs
    -0.40
     assinatura
    -0.36
    RotationOrder
    -0.36
     مواليد
    -0.34
     undef
    -0.32
     ail
    -0.32
    ClientSize
    -0.30
    出版年
    -0.30
     Finest
    -0.30
    TypedDataSet
    -0.29
    POSITIVE LOGITS
     Lightboxes
    0.57
     Infór
    0.52
     незавершена
    0.51
    EndContext
    0.50
     الرياضيه
    0.49
     Deserialize
    0.48
     beginnetje
    0.46
     âgées
    0.45
    haviors
    0.44
    %)$
    0.44
    Activations Density 0.128%

    No Known Activations