© 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 EvalsExportsinterp-engineNEWAPI 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. 14342
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conceptual understanding and iterations of the term "con."

    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
     varandra
    -0.97
     plais
    -0.95
     HasFactory
    -0.87
    feitura
    -0.85
    ArrowToggle
    -0.83
    berdayakan
    -0.82
    bebasan
    -0.82
     Efq
    -0.81
     Edad
    -0.80
    migrationBuilder
    -0.80
    POSITIVE LOGITS
    Con
    1.56
     Con
    1.51
     CON
    1.47
    CON
    1.38
    con
    1.35
     con
    1.10
    Connie
    1.08
     cones
    1.07
     Connie
    1.07
     Condo
    1.06
    Activations Density 0.241%

    No Known Activations