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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8428
    Prev
    Next
    INDEX
    Explanations

    references to traditional practices and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eynman
    -0.83
     parlent
    -0.82
     auraient
    -0.77
     незавершена
    -0.77
     Lorca
    -0.73
     Lough
    -0.72
    xase
    -0.71
     rencont
    -0.71
     Qar
    -0.70
    tauscht
    -0.69
    POSITIVE LOGITS
     Traditional
    1.38
    Traditional
    1.31
     traditions
    1.29
     traditional
    1.27
     tradi
    1.27
     tradition
    1.27
    TRAD
    1.18
    traditional
    1.16
     Tradition
    1.16
    ditionally
    1.13
    Activations Density 0.059%

    No Known Activations