Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1228
    Prev
    Next
    INDEX
    Explanations

    terminology related to foreign keys and database constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    foreign key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useAppContext
    -0.73
    ngdoc
    -0.59
    ValueStyle
    -0.57
     yyl
    -0.54
    providedIn
    -0.53
    encodeWith
    -0.53
    IContainer
    -0.52
    #
    -0.52
    BASEPATH
    -0.51
     initComponents
    -0.50
    POSITIVE LOGITS
    foreign
    0.87
     foreign
    0.77
     Foreign
    0.70
    HasForeignKey
    0.69
    Foreign
    0.66
    FOREIGN
    0.63
     FOREIGN
    0.63
    HomeAsUpEnabled
    0.46
     étrangère
    0.45
    ConstraintMaker
    0.45
    Activations Density 0.001%

    No Known Activations