Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4009
    Prev
    Next
    INDEX
    Explanations

    key terms related to diagnosis and patient experiences

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

    followed by articles or pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronoun he him

    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
    PRNewswire
    -0.75
    Geplaatst
    -0.74
     htons
    -0.72
     Efq
    -0.72
    TintMode
    -0.70
     Мексичка
    -0.70
    Hochspringen
    -0.69
     yourselves
    -0.69
    ValueStyle
    -0.68
    SizeF
    -0.66
    POSITIVE LOGITS
    這位
    1.01
    这位
    0.91
     him
    0.80
    此人
    0.67
    him
    0.62
    那位
    0.61
    那人
    0.58
     he
    0.55
    对方
    0.55
    對方
    0.54
    Activations Density 0.601%

    No Known Activations