© 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. 37-GEMMASCOPE-RES-16K
    11. 2948
    Prev
    Next
    INDEX
    Explanations

    terms related to jury sequestration and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.64
     ModelExpression
    -0.64
     protoimpl
    -0.61
    queryInterface
    -0.57
     ProtoMessage
    -0.57
    Predecesor
    -0.56
    TypedDataSet
    -0.56
    ConstraintMaker
    -0.55
     disambiguazione
    -0.55
     resourceCulture
    -0.55
    POSITIVE LOGITS
     isolation
    2.81
     isolated
    2.55
     Isolation
    2.44
     isolating
    2.38
     isolate
    2.34
    Isolation
    2.28
    isolation
    2.28
     Isolated
    2.28
     isol
    2.23
    isolated
    2.22
    Activations Density 0.684%

    No Known Activations