© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30096
    Prev
    Next
    INDEX
    Explanations

    references to the structure and participants involved in a clinical trial

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

    official roles and representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Thousands
    -0.55
    ghijkl
    -0.54
    InputBorder
    -0.54
     Lordships
    -0.54
     Corollary
    -0.54
    SequentialGroup
    -0.53
    ويل
    -0.52
    unknownFields
    -0.52
     bowlers
    -0.51
    onActivityResult
    -0.51
    POSITIVE LOGITS
     representative
    0.77
    represent
    0.71
     pinulongan
    0.69
     representatives
    0.68
     représentants
    0.68
     officio
    0.65
    Represent
    0.64
     REPRESENT
    0.64
     member
    0.63
     representation
    0.63
    Activations Density 0.234%

    No Known Activations