© 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. 34-GEMMASCOPE-RES-16K
    11. 9240
    Prev
    Next
    INDEX
    Explanations

    text that indicates disclaimers and limitations of liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     two
    -0.37
    Requ
    -0.37
     concern
    -0.36
     really
    -0.36
    undrum
    -0.35
     secret
    -0.35
    なくても
    -0.35
     Yup
    -0.35
     yes
    -0.34
     Fortunately
    -0.34
    POSITIVE LOGITS
    featureID
    0.79
    あくまで
    0.79
    GEBURTSDATUM
    0.77
     typelib
    0.75
    ftagPool
    0.75
    DISCLAIMER
    0.75
    httphttps
    0.75
    elemField
    0.74
     disclaimer
    0.71
    LookAnd
    0.69
    Activations Density 0.421%

    No Known Activations