© 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. 0-GEMMASCOPE-RES-16K
    11. 9384
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "inadvertently" and related concepts of unintended consequences or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disfr
    -0.61
     itſelf
    -0.57
     Kini
    -0.55
    subpackage
    -0.54
     bogotá
    -0.54
    かけ
    -0.53
     Unido
    -0.53
     myſelf
    -0.52
     Shakspeare
    -0.52
    ñora
    -0.49
    POSITIVE LOGITS
     inadvertently
    0.61
     inneces
    0.60
     tendency
    0.60
     forgot
    0.59
     PERMAN
    0.58
     lehet
    0.58
     tended
    0.58
    epam
    0.57
     perpendicular
    0.56
     unwittingly
    0.56
    Activations Density 2.675%

    No Known Activations