© 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. 41-GEMMASCOPE-RES-16K
    11. 6198
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and legislative requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taliban
    -0.51
     Thessalon
    -0.50
     Sarajevo
    -0.49
     barrio
    -0.49
     bruja
    -0.48
     Mahomet
    -0.48
     cabaña
    -0.48
    вгений
    -0.48
     Constantinople
    -0.47
     Antalya
    -0.47
    POSITIVE LOGITS
    nation
    0.59
    northeast
    0.58
    city
    0.56
    east
    0.53
    nations
    0.52
    land
    0.51
    town
    0.51
    urban
    0.51
    southeast
    0.50
     ExecuteAsync
    0.49
    Activations Density 0.725%

    No Known Activations