© 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. 6436
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to functions in theoretical physics

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

    TeX markup

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and equations

    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
    verifyException
    -0.69
    Vidite
    -0.66
    GEBURTSDATUM
    -0.65
    numerusform
    -0.64
    richTextPanel
    -0.61
     архивлан
    -0.60
    keyColumn
    -0.60
    Portail
    -0.59
    SharedDtor
    -0.57
    GraphicsUnit
    -0.57
    POSITIVE LOGITS
     colspan
    0.80
    ="
    0.67
    ########.
    0.57
    ––––
    0.57
    ieteur
    0.57
    ínez
    0.56
    =").
    0.55
     ['./
    0.55
    évaluateur
    0.55
    thew
    0.55
    Activations Density 0.013%

    No Known Activations