© 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. 3-GEMMASCOPE-RES-16K
    11. 10689
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with monetary figures or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     überrascht
    -0.50
     sportowe
    -0.47
    zelfde
    -0.47
     gesteld
    -0.47
     illustratie
    -0.47
     voelen
    -0.46
     advertencia
    -0.46
    equilibrio
    -0.45
     dipasang
    -0.45
     gärna
    -0.45
    POSITIVE LOGITS
    fromnode
    0.60
     كومونز
    0.60
     thousand
    0.60
     THOUS
    0.60
     oprot
    0.57
     thousands
    0.56
     millions
    0.56
     ""],
    0.56
    +#+#
    0.56
    thousand
    0.55
    Activations Density 0.203%

    No Known Activations