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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11780
    Prev
    Next
    INDEX
    Explanations

    concepts related to data management and processing efficiency

    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
    RegressionTest
    -0.41
    Insufficient
    -0.37
    :][
    -0.37
     unsuccessfully
    -0.36
     Too
    -0.35
     Cla
    -0.34
     Ang
    -0.34
     Insufficient
    -0.33
     TOO
    -0.33
     Thursday
    -0.32
    POSITIVE LOGITS
    unlike
    0.70
     unlike
    0.69
     Disadvantages
    0.64
     eliminates
    0.60
    相比
    0.60
     inherently
    0.60
    Unlike
    0.60
     Unlike
    0.59
     dibanding
    0.59
    不像
    0.59
    Activations Density 0.654%

    No Known Activations