© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3770
    Prev
    Next
    INDEX
    Explanations

    references to "car" and "administration" 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engagement
    -0.45
    onedDateTime
    -0.44
    matis
    -0.43
    Christy
    -0.43
     dirigente
    -0.43
    resent
    -0.42
    tagHelperRunner
    -0.42
    engagement
    -0.41
    renn
    -0.40
     Rican
    -0.39
    POSITIVE LOGITS
     admin
    0.98
     Admin
    0.92
     administration
    0.92
    admin
    0.89
     administering
    0.88
     Administration
    0.83
     administer
    0.83
    Admin
    0.79
     ADMINISTRATION
    0.77
    administration
    0.76
    Activations Density 0.214%

    No Known Activations