© 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
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9780
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of conditions or actions being done to the highest degree or extent possible

    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
    正
    -0.33
    Бахар
    -0.33
     igual
    -0.33
    kháu
    -0.32
    greenrobot
    -0.31
    頭
    -0.31
    importanza
    -0.30
    ãy
    -0.30
     pieza
    -0.29
     Ch
    -0.29
    POSITIVE LOGITS
     poffible
    1.05
     feasible
    0.98
     possible
    0.97
     practicable
    0.89
    possible
    0.85
    Possible
    0.80
     possível
    0.80
     POSSIBLE
    0.76
     allowable
    0.74
     Possible
    0.73
    Activations Density 0.246%

    No Known Activations