© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9021
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and phrases related to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.49
    EndGlobalSection
    -0.47
    soort
    -0.43
    ToDecimal
    -0.42
     @"/
    -0.42
     Kindes
    -0.42
    Географиясе
    -0.41
    foot
    -0.41
     démarches
    -0.39
    disposing
    -0.39
    POSITIVE LOGITS
     ProtoMessage
    0.77
    EndContext
    0.65
     viewDidLoad
    0.62
    addContainerGap
    0.62
     kaynağından
    0.61
    matchCondition
    0.59
    TRAILING
    0.59
    MigrationBuilder
    0.59
    stateProvider
    0.58
     JpaRepository
    0.55
    Activations Density 0.306%

    No Known Activations