© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions and collective sentiments

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

    Follows "We" or "we"

    np_acts-logits-general · gemini-2.0-flash

    we followed by verb

    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
     conmigo
    -0.86
     comigo
    -0.82
     asegurarse
    -0.69
    私に
    -0.69
     himself
    -0.68
     dirinya
    -0.64
    等我
    -0.64
    himself
    -0.63
    ผม
    -0.63
     Itself
    -0.61
    POSITIVE LOGITS
     ourselves
    2.70
     our
    1.78
     we
    1.54
     We
    1.53
     Our
    1.48
    Our
    1.46
    We
    1.42
    our
    1.37
     можем
    1.30
     OUR
    1.29
    Activations Density 1.071%

    No Known Activations