© 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. 934
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms associated with cultural or scientific topics, particularly related to certain families of proteins

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

    starting with "T" followed by two other letters

    np_acts-logits-general · gemini-2.0-flash

    Tats, Tacs, Tase, Tet

    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
     humaines
    -0.61
     rayons
    -0.56
    enumii
    -0.54
    onAttach
    -0.53
     lourdes
    -0.51
    GEBURTSDATUM
    -0.50
    IntoConstraints
    -0.50
     éti
    -0.49
     coloris
    -0.49
    wasser
    -0.47
    POSITIVE LOGITS
     protoimpl
    0.71
    佗
    0.64
     transférez
    0.59
    erializer
    0.58
    ddots
    0.58
    Magnum
    0.57
     ErrInvalid
    0.56
     jScrollPane
    0.55
    kmäler
    0.54
     Magnum
    0.54
    Activations Density 0.141%

    No Known Activations