© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 8821
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly in the context of their roles or contributions to particular fields or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Välislingid
    -0.67
    atguigu
    -0.59
    Personendaten
    -0.57
    %)$
    -0.56
     Elen
    -0.56
    wiss
    -0.53
    klen
    -0.52
    zzi
    -0.51
    ilish
    -0.51
    д
    -0.51
    POSITIVE LOGITS
    ه
    0.68
    a
    0.57
     naudoti
    0.52
    ה
    0.52
     ciudadana
    0.49
     głó
    0.49
     almendras
    0.49
     ambientale
    0.49
    서는
    0.49
     mał
    0.48
    Activations Density 2.711%

    No Known Activations