© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 35
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases related to contacting or calling someone

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

    Follow-up after communication

    np_acts-logits-general · gemini-2.0-flash

    initiating contact or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.66
     endregion
    -0.62
     TextAppearance
    -0.61
     SIMBAD
    -0.59
    écnicas
    -0.57
    GeoNames
    -0.57
    resave
    -0.56
    rouvez
    -0.56
     Catholicism
    -0.54
     Zapo
    -0.54
    POSITIVE LOGITS
     us
    0.76
     me
    0.69
     them
    0.61
    ReusableCell
    0.60
     StatefulWidget
    0.52
    Notify
    0.50
    Directory
    0.50
     notify
    0.49
     terlebih
    0.49
     keber
    0.49
    Activations Density 0.114%

    No Known Activations