© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    references to data structure types, particularly those related to lists and collections

    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
    AndEndTag
    -0.52
    MigrationBuilder
    -0.47
    <bos>
    -0.46
     planète
    -0.44
     universal
    -0.42
    #
    -0.39
    UseVisualStyle
    -0.35
    queryInterface
    -0.35
    ClientSize
    -0.35
    hyperref
    -0.35
    POSITIVE LOGITS
    HashMap
    1.17
     HashMap
    1.09
    ArrayList
    1.05
     ArrayList
    1.04
    URLException
    0.68
     TreeMap
    0.66
     HashSet
    0.65
    HashSet
    0.65
     LinkedHashMap
    0.60
    LinkedList
    0.57
    Activations Density 0.142%

    No Known Activations