© 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. 2-GEMMASCOPE-RES-16K
    11. 10392
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the title "Dr" or related to medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.51
    featureID
    -0.46
     onBind
    -0.45
    .*")]
    -0.44
     estekak
    -0.44
    Gambas
    -0.44
     gamme
    -0.41
    fjspx
    -0.41
     lenker
    -0.41
    iliki
    -0.40
    POSITIVE LOGITS
     Dr
    3.00
    Dr
    2.83
     Doctor
    2.69
     doctor
    2.52
    Doctor
    2.50
     dr
    2.42
    doctor
    2.28
     DOCTOR
    2.19
     доктор
    1.99
     docteur
    1.98
    Activations Density 0.129%

    No Known Activations