© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 237
    Prev
    Next
    INDEX
    Explanations

    the name "John" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    //=
    -0.82
     Lakeside
    -0.80
     ADE
    -0.76
     ſche
    -0.74
     themſelves
    -0.74
     ſind
    -0.74
     artig
    -0.73
    setMsg
    -0.72
     esimer
    -0.71
     Rache
    -0.71
    POSITIVE LOGITS
     John
    1.35
    John
    1.16
    JOHN
    1.12
     john
    1.10
     JOHN
    1.08
     Johns
    1.02
    john
    0.99
     Lennon
    0.96
     Deere
    0.94
     Johnnie
    0.93
    Activations Density 0.030%

    No Known Activations