© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2335
    Prev
    Next
    INDEX
    Explanations

    expressions of wishing or hoping for someone's well-being

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

    "wish" and its variations

    np_acts-logits-general · gemini-2.0-flash

    wish that or wish to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.66
    hedral
    -0.63
    ReusableCell
    -0.62
    mappedBy
    -0.58
    InStock
    -0.56
     ete
    -0.56
    thet
    -0.55
    complexType
    -0.55
     localObject
    -0.54
    hemiah
    -0.53
    POSITIVE LOGITS
     wish
    1.20
     Wish
    1.17
    wish
    1.16
    Wish
    1.14
     WISH
    1.14
     wished
    0.98
     Wishes
    0.95
     wishing
    0.95
     wishes
    0.92
     Wishing
    0.84
    Activations Density 0.040%

    No Known Activations