© 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. 12518
    Prev
    Next
    INDEX
    Explanations

    key terms related to claims and criteria in legal or formal documents

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

    Tokens preceding logical conclusions

    np_acts-logits-general · gemini-2.0-flash

    therefore thus hence

    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
     участи
    -0.46
     [](
    -0.46
     himſelf
    -0.45
    ftance
    -0.44
    ']))
    -0.43
    enej
    -0.43
     Toujours
    -0.43
    ())))
    -0.42
    covery
    -0.42
    UnknownFields
    -0.42
    POSITIVE LOGITS
     therefore
    3.63
    therefore
    3.04
    Therefore
    2.64
     thus
    2.61
     Therefore
    2.59
     portanto
    2.45
     donc
    2.41
     dunque
    2.32
     hence
    2.25
     quindi
    2.25
    Activations Density 1.014%

    No Known Activations