© 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. 9924
    Prev
    Next
    INDEX
    Explanations

    the word "like" or its variations in context

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

    Comes before "that," "fiber," "CP," or similar

    np_acts-logits-general · gemini-2.0-flash

    for example

    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
     ſeveral
    -0.60
    parsedMessage
    -0.57
    hip
    -0.55
     raiſ
    -0.54
     ſame
    -0.53
     feveral
    -0.52
     ſy
    -0.51
     ſuch
    -0.51
     Jefus
    -0.50
     XNUMX
    -0.49
    POSITIVE LOGITS
     ours
    0.85
     those
    0.85
    DockStyle
    0.81
    extAlignment
    0.79
     misalnya
    0.72
     this
    0.70
    เดียว
    0.70
     like
    0.70
     Мексичка
    0.69
     these
    0.68
    Activations Density 0.151%

    No Known Activations