© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4884
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal terms and processes, particularly those involving convictions, approvals, and patents

    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
    мат
    -0.48
     still
    -0.48
     للمعارف
    -0.47
    _();
    -0.47
     unknownFields
    -0.46
    MLLoader
    -0.46
    EndInit
    -0.45
    🚨
    -0.44
    spectos
    -0.44
    mtable
    -0.44
    POSITIVE LOGITS
    iastes
    0.66
     canst
    0.66
    Попис
    0.62
    ArgsConstructor
    0.60
     himſelf
    0.60
    EndContext
    0.60
    BeginContext
    0.59
     joaat
    0.58
    ftagPool
    0.57
     Jefus
    0.57
    Activations Density 0.782%

    No Known Activations