© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12-GEMMASCOPE-RES-16K
    11. 2501
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or procedural contexts, particularly those related to regulations and actions taken under established guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.83
     plufieurs
    -0.81
    väg
    -0.76
     ainfi
    -0.73
     itſelf
    -0.72
    contentLoaded
    -0.69
     pleaſure
    -0.67
     myſelf
    -0.67
    featureID
    -0.66
    évaluateur
    -0.65
    POSITIVE LOGITS
     under
    1.92
     Under
    1.73
    under
    1.69
    Under
    1.68
     UNDER
    1.55
    UNDER
    1.34
     unter
    1.23
     sous
    1.06
     underneath
    1.06
     под
    1.05
    Activations Density 0.227%

    No Known Activations