© 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. 10406
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and requests for help or suggestions

    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
    ContentAlignment
    -0.39
    Климат
    -0.32
    CloseOperation
    -0.31
    mobileqq
    -0.31
     traj
    -0.31
     contag
    -0.31
     fil
    -0.31
     dire
    -0.31
    大胆
    -0.31
     voetballer
    -0.31
    POSITIVE LOGITS
     thank
    2.59
     Thank
    2.34
    Thank
    2.14
     thanks
    2.08
    thank
    2.06
     THANK
    2.05
     thanked
    2.00
     Thanks
    1.94
     thanking
    1.87
    thanks
    1.83
    Activations Density 0.446%

    No Known Activations