© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 337
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "William"

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

    Followed by the second name of "William"

    np_acts-logits-general · gemini-2.0-flash

    William followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.69
    masing
    -0.66
    CompleteListener
    -0.66
    참고
    -0.61
     ivelany
    -0.61
     InputDecoration
    -0.60
    """)
    -0.60
    BeginInit
    -0.60
    ︎
    -0.60
    argout
    -0.59
    POSITIVE LOGITS
    boards
    0.53
     Ruto
    0.52
    ITT
    0.52
     Shakespeare
    0.51
    /**
    0.51
    前は
    0.48
    liam
    0.47
    baum
    0.46
    ("%.
    0.46
    itim
    0.45
    Activations Density 0.056%

    No Known Activations