© 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. 2244
    Prev
    Next
    INDEX
    Explanations

    subjective statements about personal beliefs and experiences

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

    Followed by the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be"

    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
     AttributeSet
    -0.73
     Did
    -0.65
    Did
    -0.64
    did
    -0.64
     did
    -0.61
    lasty
    -0.55
    aughey
    -0.54
    Does
    -0.52
    does
    -0.51
    styleable
    -0.50
    POSITIVE LOGITS
     is
    1.38
     are
    1.05
     là
    0.94
     είναι
    0.90
    是
    0.86
     être
    0.85
     essere
    0.83
     be
    0.79
     бути
    0.78
     být
    0.77
    Activations Density 0.365%

    No Known Activations