© 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. 36-GEMMASCOPE-RES-16K
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    instances of the word "policy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verhältnisse
    -0.39
     turysty
    -0.39
     kultury
    -0.39
     tasche
    -0.38
     humains
    -0.37
     définiti
    -0.36
     zdar
    -0.35
     voluntarios
    -0.33
     bū
    -0.32
     zijne
    -0.32
    POSITIVE LOGITS
     makers
    0.91
    maker
    0.84
    makers
    0.82
     maker
    0.70
    making
    0.66
     Makers
    0.65
    holders
    0.62
     Maker
    0.60
    Maker
    0.59
     Policy
    0.55
    Activations Density 0.067%

    No Known Activations