© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8814
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific letters and symbols, particularly focusing on variations of "w"

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

    The letter "w"

    np_acts-logits-general · gemini-2.0-flash

    w signals

    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
    DeclareMath
    -0.62
    abetes
    -0.52
     initComponents
    -0.52
    ViewChild
    -0.49
     Numerade
    -0.47
     Blick
    -0.47
    offsetof
    -0.45
    жет
    -0.45
    最快更新
    -0.45
     BOTTOM
    -0.44
    POSITIVE LOGITS
     w
    0.79
     W
    0.79
    W
    0.69
     vänt
    0.66
     تانيه
    0.62
     endwhile
    0.62
    w
    0.62
    Jîn
    0.61
     numberWith
    0.61
     betweenstory
    0.61
    Activations Density 0.126%

    No Known Activations