© 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. 0-GEMMASCOPE-RES-16K
    11. 1205
    Prev
    Next
    INDEX
    Explanations

    the concept of "wholeness" or completeness in a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.59
     disambiguazione
    -0.52
     dysplasia
    -0.49
     defStyleAttr
    -0.47
    RegressionTest
    -0.46
    tolerance
    -0.45
     Organiser
    -0.45
    DAOImpl
    -0.45
    ENNE
    -0.45
     Forecasts
    -0.45
    POSITIVE LOGITS
     whole
    2.64
    whole
    2.41
     entire
    2.39
    entire
    2.36
    Entire
    2.25
     ENTIRE
    2.23
     Entire
    2.22
     WHOLE
    2.17
     entirety
    2.09
    Whole
    2.03
    Activations Density 0.147%

    No Known Activations