© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15511
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving square roots

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

    "sqrt" function

    np_acts-logits-general · gemini-2.0-flash

    mathematical square root expressions

    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
    DockStyle
    -0.48
    ngdoc
    -0.47
     Cambrian
    -0.46
    abestanden
    -0.46
     funzionalità
    -0.45
    principalColumn
    -0.45
    delà
    -0.45
    msgSender
    -0.44
    astéroïdes
    -0.44
    WithMany
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.75
    ⓘ
    0.70
    SourceChecksum
    0.69
    hyrchwyd
    0.67
    )))))
    0.58
     للمعارف
    0.57
    ')")
    0.57
    StructEnd
    0.54
     Ause
    0.54
     therewith
    0.53
    Activations Density 0.593%

    No Known Activations