© 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. 35-GEMMASCOPE-RES-16K
    11. 10621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions, decisions, and conditions related to trust and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.70
     kaarangay
    -0.62
     ویکی‌پدی
    -0.57
     Signalez
    -0.51
     contextLoads
    -0.50
     Infórmanos
    -0.50
     Wiktionnaire
    -0.49
    UserScript
    -0.49
    новниш
    -0.48
    StructEnd
    -0.48
    POSITIVE LOGITS
     must
    2.56
    must
    2.17
     need
    2.11
    Must
    2.05
     Must
    2.05
     gotta
    1.96
    ต้อง
    1.90
     phải
    1.89
     MUST
    1.83
    必须
    1.81
    Activations Density 2.425%

    No Known Activations