© 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. 30-GEMMASCOPE-RES-16K
    11. 11774
    Prev
    Next
    INDEX
    Explanations

    instances of the word "con" and its derivatives in various forms

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

    Following "Con" prefix

    np_acts-logits-general · gemini-2.0-flash

    words starting with con

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abschied
    -0.38
    istiwa
    -0.35
     esta
    -0.33
     erfahren
    -0.31
     Ra
    -0.31
     eben
    -0.30
     halben
    -0.29
     Gefahren
    -0.29
     Abenteuer
    -0.29
     Nachmittag
    -0.29
    POSITIVE LOGITS
     Biôgrafia
    0.75
    principalColumn
    0.72
    IContainer
    0.68
     Con
    0.66
     Conc
    0.66
     Conn
    0.66
     autorytatywna
    0.66
     conc
    0.66
    COMPET
    0.65
    Con
    0.64
    Activations Density 0.341%

    No Known Activations