© 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. 9798
    Prev
    Next
    INDEX
    Explanations

    aspects related to dining experiences and social interactions

    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
    msgid
    -0.31
    MessageState
    -0.28
     cour
    -0.27
     REP
    -0.27
    几次
    -0.27
    InputBorder
    -0.27
     conf
    -0.27
     Repe
    -0.27
     selection
    -0.26
     alumínio
    -0.26
    POSITIVE LOGITS
    两个人
    0.92
    二人
    0.89
    三人
    0.88
    一人
    0.87
     berdua
    0.86
    兩人
    0.85
     solo
    0.81
    四人
    0.79
    两人
    0.75
     duos
    0.73
    Activations Density 0.251%

    No Known Activations